agentleFS
YehudaFrankelYehudaFrankel/clankbrain/.claude/skills/progress-report/SKILL.md

progress-report

Skill16 starsChanged 7 months agoMITView on GitHub

Shows concrete numbers proving the system is compounding. Run after session 5 or any time the user wants to see the value. Triggers on \"progress report\", \"how am I doing\", \"show my progress\", \"is this working\", \"what has the kit done for me\".

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handoff.

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.
  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    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:

    Allowed Tools: Read, Grep

    line 14
  2. Distinctive:

    If sessions < 5: "Keep going — the compounding becomes visible around session 10."

    line 50
  3. Very specific:

    If any skill has 2+ Y scores: "Run /evolve — [skill] has failed twice and is ready to patch."

    line 51
  4. Distinctive:

    If regret.md has 0 entries: "Add your first rejected approach to regret.md — it's the highest-leverage thing you can do."

    line 52
  5. Very specific:

    If lessons.md has 0 entries: "Run /learn at the end of your next session — nothing compounds without extraction."

    line 53
  6. Distinctive:

    Keep the report short — the goal is to make compounding visible, not overwhelming

    line 60

“Common” is measured: kept by at least 6 in 10 of the 4 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

Skill: progress-report

Trigger: "progress report", "how am I doing", "show my progress", "is this working", "what has the kit done for me"

Description: Shows concrete numbers proving the system is compounding. Run after session 5 or any time the user wants to see the value.

Allowed Tools: Read, Grep


Steps

  1. Read these files and count:

    • lessons.md — count ## headings = lessons accumulated
    • tasks/regret.md — count ## or | table rows = rejected approaches permanently blocked
    • error-lookup.md — count ## or | table rows = known errors never debugged twice
    • tasks/skill_scores.md — count N rows vs Y rows = skill success rate
    • STATUS.md — extract session number = sessions logged
  2. Format the report:
=== Clankbrain Progress Report ===

  Sessions logged          [N]
  Lessons accumulated      [N]   ← patterns Claude applies every session
  Rejected approaches      [N]   ← bad ideas permanently blocked
  Known errors logged      [N]   ← bugs never debugged twice
  Skill accuracy           [N]%  ← N / (N + Y) from skill_scores.md

  [One of these based on session count:]
  → Session 1-5:  "Early days. The system is learning your codebase."
  → Session 6-15: "Compounding has started. Keep the End Session habit."
  → Session 16-30: "The system knows your patterns. Regret guard is active."
  → Session 30+:  "Deep compounding. Claude knows your codebase better than most teammates would."

  Biggest win so far: [pick the most specific/interesting lesson from lessons.md]
  Approaching: [pick any skill with 2+ Y scores — next /evolve will patch it]
  1. Surface the next action:
    • If sessions < 5: "Keep going — the compounding becomes visible around session 10."
    • If any skill has 2+ Y scores: "Run /evolve — [skill] has failed twice and is ready to patch."
    • If regret.md has 0 entries: "Add your first rejected approach to regret.md — it's the highest-leverage thing you can do."
    • If lessons.md has 0 entries: "Run /learn at the end of your next session — nothing compounds without extraction."

Notes

  • Auto-suggest this skill at Start Session when session number crosses 5, 10, 20, 50
  • Keep the report short — the goal is to make compounding visible, not overwhelming
  • The "biggest win" line is the most motivating part — make it specific and concrete

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.