- Home
- Skills
- Code Quality & Review
- 17 — Scar Gardener · Complete Edition
Works with the AI Agents you already use
17 — Scar Gardener · Complete Edition
Retains correction lineage and positive/negative regression design, adding project style checks, accurate status wording and protection against overcorrection.
$25
17 — Scar Gardener · Complete Edition
Example session with this skill installed
Everyday request
I keep correcting the same status wording. Turn this exact correction into examples and checks that catch the mistake without banning legitimate uses.
For a reproducible local example, use the included synthetic structured fixture:
{
"correction": "Describe a message as drafted until actual sending is evidenced.",
"cases": [
{
"id": "prepared",
"text": "Draft ready for review.",
"required": [
"Draft"
],
"forbidden": [
"Sent"
],
"expected_pass": true
},
{
"id": "premature",
"text": "Sent to the client.",
"required": [
"Draft"
],
"forbidden": [
"Sent"
],
"expected_pass": false
},
{
"id": "actual-confirmed",
"text": "Sent; delivery receipt attached.",
"required": [
"Sent",
"receipt"
],
"forbidden": [],
"expected_pass": true
}
]
}
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
Scar Gardener — 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
Correction: Describe a message as drafted until actual sending is evidenced.
- prepared: rule passes; expected behavior matched
- premature: rule fails; expected behavior matched
- actual-confirmed: rule passes; expected behavior matched
Explicit case-sensitive text checks, not a semantic or psychological judgment
Complete structured result
{
"boundary": "Explicit case-sensitive text checks, not a semantic or psychological judgment",
"cases": [
{
"forbidden_found": [],
"id": "prepared",
"matches_expected": true,
"missing": [],
"rule_pass": true
},
{
"forbidden_found": [
"Sent"
],
"id": "premature",
"matches_expected": true,
"missing": [
"Draft"
],
"rule_pass": false
},
{
"forbidden_found": [],
"id": "actual-confirmed",
"matches_expected": true,
"missing": [],
"rule_pass": true
}
],
"correction_exact": "Describe a message as drafted until actual sending is evidenced."
}
Executed Thirsty-lang calculation
module conclave: core
drink result = 3
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 a correction—“call it a draft until sending is evidenced”—into tests that catch premature completion claims without banning legitimate sent-status reports.
Illustrative specialist response: Preserve the exact correction and context. Include a prepared-draft case, a premature sent-claim case and a legitimately evidenced sent-status neighbor. Keep the expected distinction scoped to those conditions. The included utility performs explicit case-sensitive text checks; semantic interpretation and action evidence still need review by the host agent. Promote a lasting rule only within the accepted scope and keep its change history.
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
Scar Gardener — Complete Edition
Make the correction survive the next attempt.
Retains correction lineage and positive/negative regression design, adding project style checks, accurate status wording and protection against overcorrection.
One class. 47 equipped skills. The original specialist method plus six practical everyday workflows. $25 as a one-time purchase.
For recurring writing mistakes, project-specific conventions, QA fixes and repeated assistant misunderstandings. For deeper work, the class retains its original specialist equipment and source-defined method: How can this exact correction become a bounded, reusable regression?
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 the correction and failing context without psychological interpretation.
- Extract a proposed expected behavioral distinction with exact source bindings.
- Build a positive regression that catches the original failure.
- Build neighboring negative cases that test against overgeneralization.
- Obtain human acceptance of expected behavior and scope before persistent promotion.
- Run the frozen case against candidate changes and retain failing/passing traces.
- Store a versioned lineage; later supersession does not erase history.
Specialist deliverable: correction_lineage. Its source-defined result fields are correction_source, scope, regression_cases, accepted_expectations, run_history, supersession_links. 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 specific correction into a repeatable check
Preserve the exact correction and its context. Define the expected behavioral difference and a case that would have caught the original mistake.
2. Keep a project’s actual writing preferences usable
Separate explicit preferences from inferred habits, create paired examples and retain exceptions. Do not make a local preference universal.
3. Stop drafts from being described as completed actions
Check the supplied output against actual action evidence. Distinguish a prepared message from one sent and a proposed fix from one tested.
4. Keep a fixed issue from returning
Capture the failing case, accepted correction and a minimal regression. Preserve the before/after artifacts and actual test outcome.
5. Prevent a good correction from becoming a bad blanket rule
Add nearby valid examples and counterexamples. Reject a rule that catches the original mistake by blocking intended behavior.
6. Record how a requirement evolved over time
Keep original, revised and superseded expectations with source evidence. Promote persistent behavior only within the approved scope.
Example 1 — what a specialist assignment can look like
You ask: Turn a correction—“call it a draft until sending is evidenced”—into tests that catch premature completion claims without banning legitimate sent-status reports.
Illustrative response: Preserve the exact correction and context. Include a prepared-draft case, a premature sent-claim case and a legitimately evidenced sent-status neighbor. Keep the expected distinction scoped to those conditions. The included utility performs explicit case-sensitive text checks; semantic interpretation and action evidence still need review by the host agent. Promote a lasting rule only within the accepted scope and keep its change history.
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 correcting the same status wording. Turn this exact correction into examples and checks that catch the mistake without banning legitimate uses.
The work product: A correction record, positive and neighboring negative cases, a bounded test, and a reusable review checklist.
The included local helper demonstrates a bounded part of this workflow. Its actual run on synthetic structured input produced:
Correction: Describe a message as drafted until actual sending is evidenced.
- prepared: rule passes; expected behavior matched
- premature: rule fails; expected behavior matched
- actual-confirmed: rule passes; expected behavior matched
Explicit case-sensitive text checks, not a semantic or psychological judgment
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 Scar Gardener — 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 correction record, positive and neighboring negative cases, a bounded test, and a reusable review checklist.
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)
-
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.
-
c-memory-abi-coder — Implement C11/C17 native code with checked memory and ABI-safe interfaces.
-
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-evidence-cross-examination — Cross-examine a Thirstforged Conclave result against raw observations, exact source bindings, expected predicates, and actual reviewer identity before integration.
-
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-rare-failure-cultivation — Search reproducible crash, cancellation, delay, ordering, and partial-progress schedules in disposable fixtures to expose rare CETA failures.
-
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-acceptance-crosswalk — Use for map source-defined requirements to executable acceptance evidence.
-
codex-agent-role-integrity — Use for audit codified agent contracts without renaming existing roles.
-
codex-approval-trace — Use for trace decision, requester, scope, expiry, and evidence receipts.
-
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-claim-integrity — Use for prevent observed/inferred/proposed/implemented states from being conflated.
-
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-failure-reproducer — Use for create reproducibility inputs from logs and source; do not invent successful runs.
-
codex-hostile-review — Use for challenge the implementation for bypass, risk, and missing negative evidence.
-
codex-integration-test-auditor — Use for inspect integration test entrypoints and source dependencies.
-
codex-model-integration — Use for plan and inspect model adapters without privileged execution bypass.
-
codex-negative-path-tester — Use for ensure plans include denial, bypass and negative tests.
-
codex-observability-auditor — Use for inspect recorded monitoring/log evidence without claiming telemetry deployment.
-
codex-owner-decision — Use for prepare and verify actual owner decisions, never invent approval.
-
codex-regression-isolator — Use for find regression evidence and existing test coverage before proposing correction.
-
codex-repo-preservation — Use for protect untracked work, check provenance and refuse destructive cleanup.
-
codex-root-cause-debugger — Use for inspect actual exceptions, syntax and git state to isolate observed failures.
-
codex-runtime-architecture — Use for inspect declared runtime entrypoints, interlocks and operational boundaries.
-
codex-runtime-health — Use for inspect health-related logs and configs as static evidence, not live monitoring.
-
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-language-workbench — Use Thirsty-lang as the primary local language and TSCG-B to encode/decode exact UTF-8 task and result text.
-
conclave-scar-gardener — Retains correction lineage and positive/negative regression design, adding project style checks, accurate status wording and protection against overcorrection.
-
epistemic-status-enforcer — Apply explicit epistemic status to meaningful claims.
-
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.
-
scar-gardener-correction-lineage — Record how a requirement evolved over time.
-
scar-gardener-correction-to-check — Turn a specific correction into a repeatable check.
-
scar-gardener-overcorrection-check — Prevent a good correction from becoming a bad blanket rule.
-
scar-gardener-quality-regression — Keep a fixed issue from returning.
-
scar-gardener-status-wording — Stop drafts from being described as completed actions.
-
scar-gardener-style-memory — Keep a project’s actual writing preferences usable.
-
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 17 — Scar Gardener · 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-scar-gardener/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 Code Quality & Review.
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.