agentleFS
y-miyazakiy-miyazaki/config/.claude/skills/tech-debt/SKILL.md

tech-debt

Skill1 starsChanged 10 days agoApache-2.0View on GitHub

Discover and classify technical debt from mechanical signals; apply closed-set fixes when requested. Use in conversation when the user asks to survey or fix safe documentation/dependency debt. Also the loop entry skill for scheduled scans or detect JSON. Interactive default is survey only; write agent_report_file and apply closed-set fixes when the request asks for changes to be made (for example fix, apply, or update) or automation sets agent_edit_allowed in Constraints. Do not apply structural refactors.

38 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 14 projects that use this

  • +5 more from lilangMax
  • +3 more from CoralGame

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When intent is unclear, survey and offer to apply — edits are harder to undo than a report.

    line 70
  2. Very specific:

    Read previous_report when set.

    line 76
  3. Very specific:

    IF agent_edit_allowed is false → emit survey shape with ### Candidates and optional ### Watch.

    line 78

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UTILITY SKILL — technical debt survey and closed-set apply, not structural refactor.

Input

  • Interactive (required): natural-language request; optional paths/signals — constraints in ## Constraints or category-scope.md
  • Automation (optional): detect JSON in prompt — from a caller or optional skill detect script; not required for interactive runs. Read agent_edit_allowed, agent_edit_target, and agent_report_file from ## Constraints per category-automation-envelope.md

Path allowlist, when present, arrives in ## Constraints.

Output Specification

Tech-debt report per common-output-format.md. Survey shape when agent_report_file is not written; apply shape when written — within category-scope.md.

Execution Scope

USE FOR:

  • Classify mechanical signals[] and hotspots[] into prioritized debt findings
  • Survey: emit Candidates with Delegate hints per taxonomy
  • Apply: write agent_report_file; apply closed-set fixes (broken_doc_ref, stale_doc, simple pin_drift) within allowlist

DO NOT USE FOR:

  • Structural refactors or architecture changes
  • CI repair
  • Security remediation beyond reporting
  • Edit caller state files (owned by the caller after verification)

Reference Files Guide

  • category-debt-taxonomy.md (always read)
  • common-checklist.md (always read)
  • common-output-format.md (always read)
  • category-scope.md (always read)
  • category-detect-scope.md (read on interactive path)
  • category-input-schema.md (read when detect JSON is present or the optional detect script is run)
  • category-automation-envelope.md (read on automation path)
  • common-troubleshooting.md (read on failure)
  • Previous report at previous_report (read when previous_report path exists)
  • category-pr-body-links.md (read when synthesizing the PR body)
  • assets/pr-body-template.md and assets/pr-body-template-survey.md (read when synthesizing the PR body)

Workflow

Resolve agent_edit_allowed before classifying signals:

Sourceagent_edit_allowed
Interactive — default: the request asks to look, check, triage, or survey, or only names the skillfalse — survey only; do not write agent_report_file or edit files
Interactive — the request asks for changes to be made (for example fix, apply, 修正して, 適用して, update, add)true
Interactive — follow-up after a survey asking to applytrue
Automation — ## Constraintsagent_edit_allowed: true or agent_edit_allowed: false from category-automation-envelope.md

When intent is unclear, survey and offer to apply — edits are harder to undo than a report.

When agent_edit_allowed is true, resolve agent_edit_target and agent_report_file: on the interactive path use agent_edit_target: report and agent_report_file from detect JSON (agent_report_file field) or the user request; on the automation path read both from ## Constraints. Do not branch on other caller metadata outside ## Constraints. Load category-scope.md closed-set rules before any agent_report_file write or fix.

  1. Resolve scope (category-scope.md). Parse detect JSON when present; otherwise resolve the detect universe from the prompt (category-detect-scope.md), run this skill's optional detect script with the resolved --scope (default all), then Agent-complement beyond mechanical output; if tools for detect are unavailable, gather signals/hotspots from the user request and repository tools instead of silent no-op. Load category-input-schema.md when parsing detect output. On detect script non-zero exit, read stdout and stop.
  2. On the automation path, read category-automation-envelope.md for Constraints, PR templates, and Session Metrics.
  3. Read previous_report when set. Compare per common-checklist.md EVID-02. IF detect reports skip OR both signals and hotspots are empty after gathering → emit survey no-op per common-output-format.md (Overview explains no-op); on automation path append ## Session Metrics per category-automation-envelope.md; stop.
  4. For each signal/hotspot, read ±30 lines (EVID-01). Classify per category-debt-taxonomy.md. Assign Delegate (CLASS-02).
  5. IF agent_edit_allowed is false → emit survey shape with ### Candidates and optional ### Watch; on automation path load assets/pr-body-template-survey.md at synthesis and append ## Session Metrics per category-automation-envelope.md; stop — do not write agent_report_file.
  6. ELSE IF agent_edit_allowed is true AND agent_edit_target is not report → emit survey shape; note expected agent_edit_target: report in Overview; stop — do not write agent_report_file.
  7. ELSE IF agent_edit_target is report AND (agent_report_file is missing OR empty):
    • Automation path → emit survey shape; note missing agent_report_file in Overview; stop.
    • Interactive path → apply closed-set fixes only (EDIT-01) per category-scope.md without writing a report file; emit apply shape (### Changes lists only fixed paths); note in Overview that no report file was written because no path was given. When no closed-set fix applies either, emit survey shape and offer to write the report once the user names a path.
  8. ELSE (agent_edit_allowed is true AND agent_edit_target is report AND agent_report_file is set) → write agent_report_file within allowlist with full persisted structure; apply closed-set fixes only (EDIT-01) per category-scope.md; emit apply shape with ### Changes, optional ### Deferred, and ## Verification; on automation path load assets/pr-body-template.md at synthesis and append ## Session Metrics per category-automation-envelope.md.

Error Handling

ConditionSeverityAction
Detect script non-zero exit or status: "error" (when invoked)FatalRead stdout; stop — do not treat as success-path detect JSON
skip or empty signals/hotspotsInfoEmit survey no-op (Overview explains no-op); stop
Path outside allowlist/denylistRecoverableClassify Watch; do not edit
agent_report_file outside allowlist or on denylistRecoverableDo not write the report file; note in Overview; continue closed-set fixes within allowlist
previous_report path missingRecoverableSkip comparison; note in Overview
Edit requested but ## Constraints set agent_edit_allowed: falseInfoSurvey only; note that the caller Constraints disallow edits
agent_edit_allowed true with agent_edit_target not reportRecoverableSurvey only; note expected agent_edit_target: report
agent_edit_allowed true with missing agent_report_file when agent_edit_target: reportRecoverableAutomation: survey only; note missing agent_report_file. Interactive: closed-set fixes only, no report file; note in Overview
Cap exceeded (>25 Critical+High-Priority)RecoverableRetain Critical first; defer overflow to Watch; note truncation

Examples

  • Prompt: Survey technical debt from detect JSON
  • Result: Survey report per references/common-output-format.md; write agent_report_file only when agent_edit_allowed is true and agent_edit_target is report.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.