agentleFS
Sign inStart free
CaskeyCodingCaskeyCoding/specself-starter/.claude/skills/annual/SKILL.md

annual

Skill0 starsChanged 4 months agoMITView on GitHub

Annual review (half day) — blank-slate rewrite of your principles FIRST, then diff against last year; retire what you can't re-derive. Supersedes the generic /review annual. Use for the annual tier.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Run the SpecSelf annual tier as Future-Self + Biographer + Stoic.

    line 6
  2. Very specific:

    Run the six-check coherence pass from steering/coherence.md across the rewritten stack.

    line 17
  3. Distinctive:

    Read the report's Trend section back into the wrap: a finding on a streak outranks a fresh one, so let the ONE question come from a streak …

    line 20
  4. Very specific:

    Write the rewrite and retirements as <!-- CANDIDATE - edit or delete --> blocks.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Run the SpecSelf annual tier as Future-Self + Biographer + Stoic. Honor AGENTS.md.

Read first: steering/cadence.md (annual row), steering/methodology.md, steering/coherence.md, steering/tone.md; personas future-self.md, biographer.md, stoic.md.

  1. Blank-slate rewrite FIRST. Re-derive the principles from scratch without looking at last year's set (Future-Self holds the long arc; Biographer holds the year's story).
  2. Then diff against the prior set. What you cannot re-derive is a candidate for retired. The diff between this year and last is the year's real report.
  3. Run the six-check coherence pass from steering/coherence.md across the rewritten stack; produce the ranked report. Persist it: python scripts/coherence.py your-life --write your-life/reviews/coherence --tier annual. Read the report's Trend section back into the wrap: a finding on a streak outranks a fresh one, so let the ONE question come from a streak when the trend shows one. The dated report is machine-derived and regenerable; never cite it as Evidence for a principle.
  4. Hydrate templates/review-annual.md to your-life/reviews/.

Write the rewrite and retirements as <!-- CANDIDATE - edit or delete --> blocks; recommend retirements with evidence, make none. The human authors the final set.

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.

Check your setup, free