- Home
- Skills
- Prompt & Skill Engineering
- 06 — Intent Alchemist · Complete Edition
Works with the AI Agents you already use
06 — Intent Alchemist · Complete Edition
Retains source-bound obligation compilation and semantic comparison, with everyday tools for messy briefs, careful rewrites and precise acceptance criteria.
$25
06 — Intent Alchemist · Complete Edition
Example session with this skill installed
Everyday request
Here is my messy request. Turn it into a brief I can hand to someone without losing what I meant or adding promises I never made.
For a reproducible local example, use the included synthetic structured fixture:
{
"original": "Export approved records only. Do not overwrite an existing file.",
"clauses": [
{
"id": "a",
"kind": "must",
"quote": "Export approved records only.",
"action": "export approved records"
},
{
"id": "b",
"kind": "must_not",
"quote": "Do not overwrite an existing file.",
"action": "overwrite existing file"
}
]
}
Run the class's packaged helper on that fixture. Show the readable result, full structured output, executed Thirsty calculation and the limits of what was demonstrated.
- Read your context and instructions
- Compiled the output
Intent Alchemist — real local worked example
Example type: Actual execution of the packaged structured helper on synthetic input. This is not a claimed live customer session or a full specialist-model benchmark.
Readable work product
Brief from the supplied clause classifications:
- must: export approved records — source: Export approved records only.
- must_not: overwrite existing file — source: Do not overwrite an existing file.
Conflicting clause pairs: 0
Clause classifications are supplied by the user/host agent and require semantic review
Complete structured result
{
"brief": {
"may": [],
"must": [
{
"action": "export approved records",
"id": "a",
"kind": "must",
"quote": "Export approved records only."
}
],
"must_not": [
{
"action": "overwrite existing file",
"id": "b",
"kind": "must_not",
"quote": "Do not overwrite an existing file."
}
],
"preference": [],
"unknown": []
},
"conflicts_to_resolve": [],
"interpretation": "Clause classifications are supplied by the user/host agent and require semantic review",
"original": "Export approved records only. Do not overwrite an existing file."
}
Executed Thirsty-lang calculation
module conclave: core
drink result = 2 - 0
pour result
The helper checked the language result independently, encoded the complete structured result using the published TSCG-B codec, decoded it and compared the text. Running the standalone helper generates the result files and execution receipt. The example shown here was produced on the supplied synthetic input.
The deeper specialist use
Request: Turn “export approved records only, preserve original timestamps, and ask before overwriting an existing file” into a brief and acceptance checks. Compare a rewrite that omits the overwrite condition.
Illustrative specialist response: Obligation 1: include approved records and exclude unapproved ones. Obligation 2: preserve the agreed original timestamp representation. Obligation 3: obtain approval before replacing an existing destination. Acceptance cases cover both record statuses, timestamp fidelity and an existing file with no approval. The rewrite loses the overwrite boundary and cannot be treated as equivalent. Keep the original wording next to every requirement and ask only about unresolved definitions such as the approved-status field.
The preceding specialist response is an authored illustration, not an executed external action. The original class procedures and supporting skills remain included for an actual authorized assignment.
Next step
Replace the fixture with your own task data after checking that it fits the helper's input model, or use the conversational workflow directly with your AI host. Use a fresh output directory; the helper refuses to overwrite an existing result. Review factual classifications and missing inputs before relying on the result.
Connects securely to your tools. The creator never sees your data.
About this skill
Intent Alchemist — Complete Edition
Keep the exact intent—from the first request to the final result.
Retains source-bound obligation compilation and semantic comparison, with everyday tools for messy briefs, careful rewrites and precise acceptance criteria.
One class. 47 equipped skills. The original specialist method plus six practical everyday workflows. $25 as a one-time purchase.
For turning messy requests into useful briefs, careful rewrites, acceptance criteria, and clear handoffs. For deeper work, the class retains its original specialist equipment and source-defined method: Which exact supported obligations preserve the human instruction?
What you actually receive
- All 40 original skills, including the specialist entrypoint, original supporting procedures, language workbench and evaluation lab.
- Six added everyday skills, listed in full below, and the new structured helper and worked example.
- 1 restored named dependency/dependencies: epistemic-status-enforcer.
- Class methods, contracts, source references, standalone task-packet tooling, executable helpers and worked examples, delivered through your connected AI.
- Standalone Thirsty-lang and TSCG-B tooling that uses the real
thirsty-lang==0.9.0runtime. Code execution requires Python 3.10+, a host execution tool and that separately installed package in the same environment. No runtime wheel is delivered through Agensi.
The specialist class: the original depth stays equipped
- Preserve original bytes and source coordinates before interpretation.
- Separate directives, factual claims, preferences, suggestions and hypotheticals.
- Propose obligations, prohibitions, permissions and completion predicates with exact source spans.
- Keep negation, quantity, modality, time and scope intact.
- Record unsupported assumptions and material ambiguities with affected actions.
- Submit the interpretation to the authorized semantic-review/adoption process.
- Return the proposed or accepted contract with actual adoption evidence and remaining uncertainty.
Specialist deliverable: supported_obligation_contract. Its source-defined result fields are source_spans, obligations, prohibitions, permissions, assumptions, adoption_record. These guide the work product; an actual outcome requires the task inputs, authorized tools and evidence.
Six everyday workflows — the documented practical use cases
1. Turn a stream of thoughts into an executable brief
Extract the goal, deliverable, audience, constraints and completion test. Quote the source for consequential requirements and label proposed interpretations.
2. Make a message clearer while preserving its intent
Retain commitments, uncertainty, negation and speaker roles. Produce the polished draft plus a short record of any substantive change that needs the user’s decision.
3. Make a request someone else can act on
Write what to produce, supplied inputs, permission boundaries, and what counts as complete. Keep optional ideas separate from required work.
4. Translate a request into checks that matter
Create positive, negative and boundary cases linked to the exact request. Avoid tests that merely repeat the implementation.
5. Find what a rewrite quietly changed
Compare obligations, permissions, quantities, time and scope across versions. Show each important difference with paired quotations.
6. Ask fewer, better questions
List unknowns with their consequences, proceed where the answer does not matter, and ask the smallest question that resolves a consequential ambiguity.
Example 1 — what a specialist assignment can look like
You ask: Turn “export approved records only, preserve original timestamps, and ask before overwriting an existing file” into a brief and acceptance checks. Compare a rewrite that omits the overwrite condition.
Illustrative response: Obligation 1: include approved records and exclude unapproved ones. Obligation 2: preserve the agreed original timestamp representation. Obligation 3: obtain approval before replacing an existing destination. Acceptance cases cover both record statuses, timestamp fidelity and an existing file with no approval. The rewrite loses the overwrite boundary and cannot be treated as equivalent. Keep the original wording next to every requirement and ask only about unresolved definitions such as the approved-status field.
This example illustrates the class method. It is not an assertion that the proposed external investigation, model trial or system change has been executed.
Example 2 — an everyday request
Here is my messy request. Turn it into a brief I can hand to someone without losing what I meant or adding promises I never made.
The work product: A clean brief, exact source-to-requirement links, explicit boundaries, and only the questions that materially affect the work.
The included local helper demonstrates a bounded part of this workflow. Its actual run on synthetic structured input produced:
Brief from the supplied clause classifications:
- must: export approved records — source: Export approved records only.
- must_not: overwrite existing file — source: Do not overwrite an existing file.
Conflicting clause pairs: 0
Clause classifications are supplied by the user/host agent and require semantic review
See the demo section below for its complete input, structured result and executed Thirsty calculation.
Example 3 — using the class template on your own material
Use Intent Alchemist — Complete Edition.
Goal: [the concrete result I need]
Material: [paste or attach the actual records, notes, code or facts]
Scope: [what may be inspected or changed]
Constraints: [time window, dependencies, formats and important conditions]
Deliver: A clean brief, exact source-to-requirement links, explicit boundaries, and only the questions that materially affect the work.
Use the original specialist method when the problem requires it.
Ask only for missing facts that materially change the result.
Show what you actually did and what still needs a decision.
For a simple request, use only the relevant everyday mode. For advanced work, select the original specialist procedures. Keeping the equipment available does not require loading every skill into every interaction.
Every skill available in this pack (47 total)
-
algorithm-design-forge — Invent and implement problem-specific algorithms with verified invariants and adversarial tests.
-
architecture-decision-recorder — Edition XXII source-attributed supplemental agent procedure: Architecture choice and tradeoff recording.
-
build-reproducibility-receipts — Create verifiable local build and test receipts linking source snapshots, commands and exact artifact bytes.
-
ceta-authority-timeline-autopsy — Reconstruct possible CETA event and authority histories across occurrence, recording, observation, and validity time, and identify distinguishing evidence.
-
ceta-class-router — Choose a Thirstforged Conclave sub-agent class for a CETA task, prepare its bounded assignment and exact skill inventory, and distinguish instruction packets from native profile activation.
-
ceta-cross-representation-meaning-trials — Test whether intent, obligations, schemas, UTF representations, and implementation preserve the same supported meaning, including negative and ambiguous cases.
-
ceta-evidence-cross-examination — Cross-examine a Thirstforged Conclave result against raw observations, exact source bindings, expected predicates, and actual reviewer identity before integration.
-
ceta-frame-authority-confusion — Build bounded TSCG/TSCG-B and policy specimens that separate valid framing and checksums from legitimate actor, scope, freshness, and execution authority.
-
ceta-intent-obligation-compiler — Turn a user's CETA request into traceable supported obligations while retaining exclusions, corrections, authority boundaries, ambiguity, and unresolved meaning.
-
ceta-semantic-counterfeit-forge — Construct plausible semantic mutants of authorized code or contracts, challenge them with independent oracles and differential tests, and reduce surviving counterexamples.
-
ceta-utf-contract-map — Map a CETA task to the six Universal Thirsty Family tiers and exact isolated Thirsty-Lang 0.9.0 tools, preserving the difference between analysis, integrity, and authority.
-
codex-access-control-verifier — Use for inspect configured least-privilege checks and insecure access exposure.
-
codex-api-contract-auditor — Use for inspect api definition documents, json contracts and documentation consistency.
-
codex-approval-trace — Use for trace decision, requester, scope, expiry, and evidence receipts.
-
codex-authority-resolver — Use for resolve governing clause identity and applicable authorization without assuming precedence.
-
codex-autonomy-review — Use for evaluate competence evidence and legitimate authority for autonomy changes.
-
codex-build-reproducer — Use for inventory local build ingredients and reproducibility conditions.
-
codex-change-impact — Use for review impact of source/code changes on tests and downstream records.
-
codex-claim-integrity — Use for prevent observed/inferred/proposed/implemented states from being conflated.
-
codex-conversation-fidelity — Use for audit attribution and interpret the actual speaker words without invented states.
-
codex-data-lineage — Use for trace source-data provenance and evidence status through transformations.
-
codex-evidence-ledger — Use for validate referenced evidence paths and source identity.
-
codex-hostile-review — Use for challenge the implementation for bypass, risk, and missing negative evidence.
-
codex-owner-decision — Use for prepare and verify actual owner decisions, never invent approval.
-
codex-repo-preservation — Use for protect untracked work, check provenance and refuse destructive cleanup.
-
codex-requirements-interpreter — Use for convert stated requirements into source-linked testable acceptance criteria.
-
codex-scope-guardian — Use for prevent invented or silently widened objectives and repository scope.
-
codex-source-integrity — Use for check bundled source document checksums and protect observed provenance.
-
conclave-evaluation-lab — Design held-out comparisons of the equipped agent and baseline workflows with matched models, tools, budgets, and recorded evidence.
-
conclave-intent-alchemist — Retains source-bound obligation compilation and semantic comparison, with everyday tools for messy briefs, careful rewrites and precise acceptance criteria.
-
conclave-language-workbench — Use Thirsty-lang as the primary local language and TSCG-B to encode/decode exact UTF-8 task and result text.
-
constitutional-translation-layer — Edition XXII source-attributed supplemental agent procedure: Constitutional requirement translation.
-
epistemic-status-enforcer — Apply explicit epistemic status to meaningful claims.
-
intent-alchemist-acceptance-criteria — Translate a request into checks that matter.
-
intent-alchemist-clarify-only-blockers — Ask fewer, better questions.
-
intent-alchemist-handoff-contract — Make a request someone else can act on.
-
intent-alchemist-meaning-diff — Find what a rewrite quietly changed.
-
intent-alchemist-messy-to-brief — Turn a stream of thoughts into an executable brief.
-
intent-alchemist-rewrite-with-fidelity — Make a message clearer while preserving its intent.
-
polyglot-schema-contracts — Create executable versioned data contracts across multiple programming languages.
-
polyglot-stack-selector — Select practical combinations of programming languages and runtime boundaries for one application.
-
proof-obligation-generator — Edition XXII source-attributed supplemental agent procedure: Execution proof obligation construction.
-
property-fuzz-test-engineer — Implement executable property-based tests, deterministic fuzz harnesses and failure minimization for source code.
-
python-production-coder — Implement and repair working Python applications, libraries and asynchronous services.
-
semantic-canonicalizer — Edition XXII source-attributed supplemental agent procedure: Evidence-linked semantic canonical form.
-
thirsty-work-orchestrator — Edition XXII source-attributed supplemental agent procedure: Role graph scheduling and evidence handoff.
-
type-contract-architect — Create implementable domain types and API contracts before coding.
Thirsty-lang and TSCG-B in practice
Run the packaged helper with Python 3.10+ to generate a readable result, structured JSON, the executed .thirsty calculation, a binary .tscg-b result and an execution receipt. The helper executes supported arithmetic in Thirsty-lang and independently checks the result; Python handles structured input and the domain algorithm. TSCG-B preserves result text through binary encode/decode. A valid frame does not itself prove the text is true or authorize an action.
Preservation and validation
Every original skill identity and the specialist methods remain, together with the six everyday additions and repaired named dependencies. The Agensi upload layout adapts executable scripts and reference delivery; historical source files and preservation records remain in the creator's original archive.
The repaired collection passed 409 local delivery and execution checks, including all 19 standalone class helpers, real Thirsty-lang calculations, TSCG-B round trips, exact task packets, delivery limits and negative cases. Independent checks also passed all 52 distinct audit-tool bindings and their source-index lookups. Six compiler-specific examples were not executed because their compiler dependencies were absent. These results do not establish every AI host's behavior, marketplace approval, live buyer retrieval, frontier-model superiority or revenue.
Start using it
Connect your AI to Agensi and ask: “Use my Agensi skill 06 — Intent Alchemist · Complete Edition. My goal is [result]. Here is my actual material: [notes, records or code].” The pack provides an index; your AI loads the class entrypoint skills/conclave-intent-alchemist/SKILL.md, then loads the supporting skills relevant to your task. Purchasing the pack does not automatically run all its skills at once.
Text and reasoning workflows run through your existing AI. Standalone scripts additionally require Python 3.10+ and a code execution tool. Thirsty-lang and TSCG-B execution requires thirsty-lang==0.9.0 installed separately in that environment; your AI should explain missing requirements before starting. Scripts are fetched unchanged through Agensi, executed temporarily and removed. Task result files can be delivered to you; the purchased skill is not installed as a downloadable local folder.
Image, video, voice and data services from Agensi's optional tools catalog are separate paid services. This pack does not require adding those services merely to use its text workflows or Python helpers. External actions, compiler tasks and account access still require the actual relevant host tools and your permission.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.
This is a skill/class package for an existing compatible AI host. It does not supply model weights, hosted compute, API credits, automatic account connections or permissions. The included helpers accept bounded structured inputs; they are not general document parsers or substitutes for semantic review. Their actual synthetic-fixture outputs are distinguished from authored specialist illustrations. Local preservation/tool checks do not establish correctness on arbitrary tasks, frontier-model superiority, customer results or revenue. Optional UTF analysis features may require additional dependencies. Marketplace ingestion of the final multi-skill ZIP remains subject to the receiving platform’s actual review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
- Software
Node.js
- Optional
Python 3.10+thirsty-lang==0.9.0
Text workflows use your connected AI. Code needs Python 3.10+ and an execution tool. Thirsty-lang and TSCG-B need thirsty-lang==0.9.0 installed in that environment. No hosted model or API credits are included.
Permissions
Read Files, Write Files and Terminal/Shell support the optional local examples and authorized project work. Work stays within the user-approved scope. Browser, network, services and credentials are task-dependent and are not granted by this package. A draft, recommendation or prepared payload is not evidence of an external action.