signal-first
Skill49 starsChanged 14 days agoApache-2.0View on GitHub
Shape an answer for fast scanning with result-first sentences, concrete verbs, compact structure, and selectable compression while preserving every correctness-critical detail. Use when the user asks for Caveman-style output, terse or low-token prose, executive scanning, fewer words, or a concise rewrite whose substance must remain intact.
In this repository151 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms-full.txtllms.txt
- llms.txtllms.txt
- agent-readinessSkill
- appeal-scoreSkill
- bottleneck-mapSkill
- ci-repairSkill
- claim-repro-scoreSkill
- clear-out-wipSkill
- commit-cleanSkill
- conflation-scoreSkill
- cross-validateSkill
- curate-clusterSkill
- debt-cleanSkill
- debt-orchestratorSkill
- disambiguation-scoreSkill
- dojo-rsi-scoreSkill
- dos-dispatch-loopSkill
- dos-dispatchSkill
- dos-next-upSkill
- dos-replanSkill
- dos-witness-claimSkill
- field-borrowSkill
- fleet-waveSkill
- git-subagent-syncSkill
- goalSkill
- guard-rsi-scoreSkill
- harness-creatorSkill
- harness-gardenSkill
- industry-scoreSkill
- issue-orchestratorSkill
- issue-queueSkill
- issue-triageSkill
- lightgap-scoreSkill
- memory-compactSkill
- milestone-scoreSkill
- modularizeSkill
- negframe-scoreSkill
- opencode-waveSkill
- operator-heaviness-scoreSkill
- persona-scoreSkill
- phased-planSkill
- plan-auditSkill
- quality-scoreSkill
- question-loopSkill
- refresh-cachedoc-numbersSkill
- refresh-readmeSkill
- releaseSkill
- resume-watchdog-auditSkill
- run-it-all-nightSkill
- score-2xSkill
- scorecardSkill
- scout-loopSkill
- skill-lifecycleSkill
- skill-overlapSkill
- skill-scoreSkill
- slop-scoreSkill
- sota-checkSkill
- The first 60 shown.
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
- Distinctive: line 28
Put the result, decision, or next action in the first line.
- Distinctive: line 30
Use concrete nouns and active verbs.
- Distinctive: line 32
Keep the evidence beside the claim it supports.
- Distinctive: line 46
When compression competes with correctness, keep correctness and move to a lighter level.
- Distinctive: line 53
every paragraph adds a new fact, reason, or action.
- Distinctive: line 54
every claim retains its evidence or uncertainty.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Signal First
Make the useful part easy to find and safe to act on.
Choose the compression level
Honor an explicit level. Otherwise select the lightest level that meets the request.
| Level | Shape | Best fit |
light | Answer first, then useful explanation | Teaching, unfamiliar material, nuanced decisions |
focused | Result first, then action-critical context | Default for concise work and status updates |
compressed | Short subject-first lines and dense bullets | Expert readers, repeated workflows, operational handoffs |
minimal | Shortest complete answer or requested artifact | Exact lookups, commands, confirmations, structured output |
Expand one level when the task has ambiguity, meaningful tradeoffs, safety impact, or a novice audience. Compress one level when the format is exact or the reader already has the context.
Write the answer
- Put the result, decision, or next action in the first line.
- Give each line one job.
- Use concrete nouns and active verbs.
- Group parallel facts into compact bullets or a small table.
- Keep the evidence beside the claim it supports.
- End with the next checkable action when one exists.
Preserve substance
Include every detail that keeps the answer correct and usable:
- safety boundaries and warnings;
- uncertainty, assumptions, and material tradeoffs;
- exact commands, code, identifiers, citations, and paths;
- user-requested sections and output formats;
- evidence needed to support completion or performance claims;
- accessibility and respectful professional language.
When compression competes with correctness, keep correctness and move to a lighter level.
Final pass
Confirm that:
- the first line carries the main result;
- every paragraph adds a new fact, reason, or action;
- every claim retains its evidence or uncertainty;
- the response satisfies the requested format;
- a reader can act without reconstructing omitted context.
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
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.

