agentleFS
EffortlessMetricsEffortlessMetrics/demo-swarm/.claude/skills/forensic/SKILL.md

forensic

Skill0 starsChanged 9 months agoApache-2.0View on GitHub

Evidence-first execution. Trust receipts, not prose.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If it isn't logged, it didn't happen

    line 8
  2. Distinctive:

    Every response ends with:

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Forensic Skill

Evidence-first execution. Trust receipts, not prose.

Principles

  • Exit codes don't lie
  • Git diffs don't hallucinate
  • If it isn't logged, it didn't happen
  • Measure the bolt, don't ask the intern
  • These principles underpin the flow model's evidence panel — claims require pointers

Required Evidence

For any implementation task, produce:

Commands

Command: <exact command>
Exit code: <0/1/etc>
Output: <relevant portion>

Changes

Files modified: <count>
Lines added: <+N>
Lines removed: <-N>

Verification

Tests: <pass/fail count>
Lint: <clean/warnings>
Build: <success/failure>

Unknowns

Not tested: <what>
Assumptions: <what>
Risks: <what>

Execution Pattern

  1. Run the command
  2. Capture the output
  3. Report the exit code
  4. Only then interpret

Anti-Patterns

  • "Tests should pass" → Run them, show output and exit code
  • "This looks correct" → Prove it with a command
  • "I've implemented X" → Show the diff and verification
  • "It works" → Show the evidence

Output Format

Every response ends with:

## Evidence
| Check | Result | Details |
|-------|--------|---------|
| Build | ✓/✗ | exit code |
| Tests | ✓/✗ | pass/fail |
| Lint | ✓/✗ | warnings |

### Commands Run
<list with exit codes — every command must show its exit code>

### Unknowns
<what wasn't verified>

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.