agentleFS
veep2012veep2012/doc_mcp/.agents/skills/tech-debt/SKILL.md

tech-debt

Skill0 starsChanged 3 months agoMITView on GitHub

Capture deferred technical debt discovered during development in dated markdown files under tech-debt/. Use when an issue is real, relevant, and intentionally not fixed in the current task.

36 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

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when implementation/review uncovers technical debt that should be documented now and fixed later.

    line 10
  2. Distinctive:

    If debt is actionable but out of current scope, record it immediately.

    line 13
  3. Distinctive:

    Keep debt entries concrete and traceable to code/files.

    line 14
  4. Distinctive:

    Use for any of the following:

    line 19
  5. Distinctive:

    Do not use for:

    line 25
  6. Distinctive:

    If the file exists, append a new debt item.

    line 39
  7. Distinctive:

    If it does not exist, create it with one H1 and a short purpose line.

    line 40
  8. Distinctive:

    Use precise language and concrete paths.

    line 55
  9. Distinctive:

    Avoid secrets, credentials, or personal data.

    line 56
  10. Distinctive:

    Keep each item independently actionable.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 29 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

Tech Debt

Overview

Use this skill when implementation/review uncovers technical debt that should be documented now and fixed later.

Core rule:

  1. If debt is actionable but out of current scope, record it immediately.
  2. Keep debt entries concrete and traceable to code/files.
  3. Store entries only in tech-debt/<YYYY-MM-DD>.md.

When To Use

Use for any of the following:

  • Known limitation deferred to keep scope controlled
  • Risky workaround intentionally accepted for now
  • Missing test/guard/documentation that cannot be completed in the current change
  • Design compromise that should be revisited

Do not use for:

  • Already fixed issues
  • Vague ideas with no concrete code impact
  • Product feature requests unrelated to technical quality

Workflow (Required)

Step 1: Confirm it is real debt

  • Identify exact impacted files/components.
  • State why it cannot be fixed now.
  • State risk if it remains unresolved.

Step 2: Ensure dated file exists

  • Target file: tech-debt/<YYYY-MM-DD>.md (for today).
  • If the file exists, append a new debt item.
  • If it does not exist, create it with one H1 and a short purpose line.

Step 3: Add debt item with required fields

Each item must include:

  • ID: TD-YYYYMMDD-XX
  • Title
  • Context (what was being changed when found)
  • Location (repo file paths)
  • Impact/Risk
  • Why Deferred Now
  • Proposed Fix
  • Acceptance Signal (what proves debt is resolved)
  • Status (open by default)

Step 4: Keep entries implementation-ready

  • Use precise language and concrete paths.
  • Avoid secrets, credentials, or personal data.
  • Keep each item independently actionable.

Output Requirements

Always report:

  • Dated debt file path updated/created
  • Debt item IDs added
  • Short statement of why each item was deferred

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.