agentleFS
MidnightDarlingMidnightDarling/collate/skills/chunqiu/SKILL.md

chunqiu

Skill8 starsChanged 7 months agoApache-2.0View on GitHub

Use when reading a single historical paper or final draft and you need to surface taboo, judgment, rhetorical silence, repetition, or the contemporary reality the author approaches indirectly.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Use this skill to answer four questions:

    line 22
  2. Distinctive:

    Read for the following force lines:

    line 39
  3. Distinctive:

    Do not flatten the reading into ideology-hunting.

    line 55
  4. Distinctive:

    Never overwrite the source.

    line 72
  5. Distinctive:

    Do not turn suggestive silence into false certainty.

    line 73
  6. Distinctive:

    If the text is too flat to justify this reading, say so plainly.

    line 74

≈ “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

chunqiu

The work this skill is for

The historian rarely says it directly. A title can be safe while a verb is not. A citation can be dutiful while a silence is not. This skill reads for judgment embedded in diction: the words chosen among near-synonyms, the repetitions that betray unease, the omission that does not quite manage to disappear.

It does not proofread and it does not fact-check. It reads the paper as an act of positioning.

What it asks

Use this skill to answer four questions:

  1. Which word choices carry verdicts?
  2. Where does the prose pause, repeat, or refuse to land?
  3. How is antiquity being used as a mirror for the present?
  4. What one sentence does the author most want to say without writing?

Input

Target: $ARGUMENTS

  • workspace directory → read <ws>/final.md
  • .md file → read it directly
  • empty → ask what to read

Method

Read for the following force lines:

  • Where the prose pauses, the pen fears.
  • What repeats must repeat for a reason.
  • The harder something is scrubbed clean, the blacker the original stain.
  • Seemingly unrelated digressions are often leakage.
  • What follows 然而 / 虽然 / however / granted is often what the author actually thinks.
  • Passive voice and omitted subjects often hide accountability.

Pay special attention to verdict-bearing distinctions:

  • rank-marked death verbs (卒 / 薨 / 崩)
  • punitive verbs (诛 / 弑 / 戮)
  • adjectives that moralize without declaring themselves
  • conspicuous absences where the argument ought to name someone or something directly

Do not flatten the reading into ideology-hunting. The task is not to accuse; it is to hear the pressure in the prose.

Output

  • workspace mode → <workspace>/analysis/{stem}_chunqiu.md
  • single-file mode → analysis/{stem}_chunqiu.md

Report structure:

  1. Diction verdicts — key verbs and nouns, with the implied judgment they carry
  2. Repetition and pause — recurring phrases, abrupt transitions, elisions
  3. Mirror of antiquity — where historical material is borrowed to gesture at a present concern
  4. One unsaid sentence — the line the paper circles but never writes

Guardrails

  • Never overwrite the source.
  • Do not turn suggestive silence into false certainty.
  • If the text is too flat to justify this reading, say so plainly.
  • Negative space matters: the point is to preserve the shape of the unsaid, not to vandalize it.

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.