- Home
- Skills
- Prompt & Skill Engineering
- 02 — Chimera Foundry · Complete Edition
Works with the AI Agents you already use
02 — Chimera Foundry · Complete Edition
Build a better agent. Find a better way to work. Preserves bounded skill composition and held-out trials, then applies that experimental discipline to prompts, study routines and recurring work. 47 skills. $25 one-time.
$25
02 — Chimera Foundry · Complete Edition
Example session with this skill installed
Everyday request
I keep spending an hour preparing client updates. Compare two ways to do it and design a small test that tells me which one actually helps.
For a reproducible local example, use the included synthetic structured fixture:
{
"criteria": [
{
"id": "speed",
"weight": 3
},
{
"id": "depth",
"weight": 2
}
],
"options": [
{
"id": "A",
"scores": {
"speed": 8,
"depth": 4
}
},
{
"id": "B",
"scores": {
"speed": 5,
"depth": 9
}
}
]
}
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
Chimera Foundry — 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
Preference-based ranking:
- B: 6.6 / 10
- A: 6.4 / 10
Incomplete options excluded: none
Supplied preferences and ratings, not independently measured quality
Complete structured result
{
"incomplete_excluded": [],
"ranking": [
{
"id": "B",
"score": 6.6
},
{
"id": "A",
"score": 6.4
}
],
"score_provenance": "Supplied preferences and ratings, not independently measured quality",
"tied_leaders": [
"B"
],
"without_highest_weight_criterion": [
{
"id": "B",
"score": 9.0
},
{
"id": "A",
"score": 4.0
}
]
}
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: Compare a normal review workflow with a checklist-assisted workflow. Use six practice tasks and four held-out tasks. Keep tools, model and permissions equal.
Illustrative specialist response: Candidate A keeps the baseline review. Candidate B adds the declared checklist. Freeze the rubric and candidates before exposing the four held-out tasks. Record confirmed findings, missed issues where independently known, false alarms, time and tool use. The comparison table starts unmeasured; a winner is selected only after actual trials. Failed, blocked and timed-out attempts remain in the record. The buyer receives an experiment that can distinguish an improvement from a persuasive story.
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
Chimera Foundry — Complete Edition
Build a better agent. Find a better way to work.
Preserves bounded skill composition and held-out trials, then applies that experimental discipline to prompts, study routines and recurring work.
One class. 47 equipped skills. The original specialist method plus six practical everyday workflows. $25 as a one-time purchase.
For recurring work: writing, studying, reviewing, researching, or organizing tasks. For deeper work, the class retains its original specialist equipment and source-defined method: Which bounded loadout performs better on the adopted held-out tasks?
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
- Freeze the corpus, metric definitions and candidate locks before trials.
- Reject candidates that exceed the same approved authority and resource envelope.
- Allocate matched trials and explicitly record shared model/provider and fixture dependencies.
- Run only qualified candidates through the canonical gate; retain failed, blocked and timed-out trials.
- Compare useful completion, procedure, effects and cost with denominators and uncertainty.
- Identify confounders and conditions where no ranking is supported.
- Return a candidate recommendation for owner review; adoption and activation remain separate.
Specialist deliverable: loadout_comparison. Its source-defined result fields are candidate_locks, trial_conditions, trial_results, comparison_metrics, confounders, recommendation. 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. Choose between two ways of doing your work
Hold the task and tools constant, define what good means, and vary one workflow feature. Separate measured outcomes from preference scores.
2. Improve a prompt against real examples
Preserve the intended output, make two bounded prompt variants, and test against fresh examples. Include the original prompt and each change so the user can see the tradeoff.
3. Find a study routine that fits your constraints
Use supplied learning goals, time and preferences to design two short routines. Measure recall with the same questions after the same delay; do not claim learning gains before trials.
4. Replace an annoying routine with a better candidate
Map the current steps and friction points, propose a small change, and record setup cost and fallback. Keep the experiment small enough to abandon.
5. Make preferences explicit when choices feel close
Ask for criteria and weights only where missing; score using supplied evidence. Report ties, missing values and whether the winner changes when a major criterion is removed.
6. Turn a few experiments into an honest conclusion
Keep failed attempts in the denominator, compare the same units, and distinguish an early preference from evidence of a repeatable improvement.
Example 1 — what a specialist assignment can look like
You ask: Compare a normal review workflow with a checklist-assisted workflow. Use six practice tasks and four held-out tasks. Keep tools, model and permissions equal.
Illustrative response: Candidate A keeps the baseline review. Candidate B adds the declared checklist. Freeze the rubric and candidates before exposing the four held-out tasks. Record confirmed findings, missed issues where independently known, false alarms, time and tool use. The comparison table starts unmeasured; a winner is selected only after actual trials. Failed, blocked and timed-out attempts remain in the record. The buyer receives an experiment that can distinguish an improvement from a persuasive story.
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
I keep spending an hour preparing client updates. Compare two ways to do it and design a small test that tells me which one actually helps.
The work product: Two clear candidate workflows, a fair comparison, a weighted preference table, and a recommendation tied to the available evidence.
The included local helper demonstrates a bounded part of this workflow. Its actual run on synthetic structured input produced:
Preference-based ranking:
- B: 6.6 / 10
- A: 6.4 / 10
Incomplete options excluded: none
Supplied preferences and ratings, not independently measured quality
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 Chimera Foundry — 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: Two clear candidate workflows, a fair comparison, a weighted preference table, and a recommendation tied to the available evidence.
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-delegation-collusion-trials — Construct bounded delegation and review graphs that test circular approval, identity aliasing, authority laundering, and coalition behavior against actual acceptance rules.
-
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-heldout-loadout-trials — Compare Chimera Foundry loadouts against a fixed baseline on preserved held-out tasks and report supported advantage, regression, or inconclusive evidence.
-
ceta-incentive-failure-societies — Run bounded deterministic agent-society simulations that expose incentive conflicts, metric gaming, missing stakeholders, and collective failure despite local compliance.
-
ceta-loadout-synthesis — Use the Chimera Foundry to construct bounded candidate skill loadouts from the selected inventory while preserving fixed task scope, budgets, and permissions.
-
ceta-rare-failure-cultivation — Search reproducible crash, cancellation, delay, ordering, and partial-progress schedules in disposable fixtures to expose rare CETA failures.
-
ceta-resource-pressure-reduction — Minimize a discovered fault or resource-pressure failure into a reproducible causal case while preserving measurement provenance and uncertainty.
-
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.
-
chimera-foundry-decision-matrix — Make preferences explicit when choices feel close.
-
chimera-foundry-prompt-tuneup — Improve a prompt against real examples.
-
chimera-foundry-routine-redesign — Replace an annoying routine with a better candidate.
-
chimera-foundry-study-method-fit — Find a study routine that fits your constraints.
-
chimera-foundry-trial-review — Turn a few experiments into an honest conclusion.
-
chimera-foundry-workflow-a-b — Choose between two ways of doing your work.
-
codex-acceptance-crosswalk — Use for map source-defined requirements to executable acceptance evidence.
-
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-ci-release-gate — Use for check ci test and dependency inputs before claiming release readiness.
-
codex-claim-integrity — Use for prevent observed/inferred/proposed/implemented states from being conflated.
-
codex-repo-preservation — Use for protect untracked work, check provenance and refuse destructive cleanup.
-
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-chimera-foundry — Preserves bounded skill composition and held-out trials, then applies that experimental discipline to prompts, study routines and recurring work.
-
conclave-evaluation-lab — Design held-out comparisons of the equipped agent and baseline workflows with matched models, tools, budgets, and recorded evidence.
-
conclave-language-workbench — Use Thirsty-lang as the primary local language and TSCG-B to encode/decode exact UTF-8 task and result text.
-
epistemic-status-enforcer — Apply explicit epistemic status to meaningful claims.
-
experiment-governance-designer — Edition XXII source-attributed supplemental agent procedure: Governed experiment design.
-
governed-agent-designer — Edition XXII source-attributed supplemental agent procedure: Bounded agent capability design.
-
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.
-
skill-composition-auditor — Edition XXII source-attributed supplemental agent procedure: Skill loadout conflict audit.
-
skill-dependency-resolver — Edition XXII source-attributed supplemental agent procedure: Offline-first skill dependency resolution.
-
skill-evolution-manager — Edition XXII source-attributed supplemental agent procedure: Skill version and migration control.
-
skill-regression-tester — Edition XXII source-attributed supplemental agent procedure: Skill behavior regression evaluation.
-
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 02 — Chimera Foundry · 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-chimera-foundry/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.