trim-agents-md
Tightens a repository's always-loaded agent instructions (AGENTS.md, CLAUDE.md, unconditional rules): every line must prevent a mistake, and each one that…
Skill by fblissjr
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fblissjr-trim-agents-md
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, testing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/trim-agents-md
What's inside
- Skill name
trim-agents-md- Description
- Tightens a repository's always-loaded agent instructions (AGENTS.md, CLAUDE.md, unconditional rules): every line must prevent a mistake, and each one that doesn't is moved to the narrowest home that loads when it matters (a path-scoped rule, a skill, a hook or test, the status doc, the user-level file) or cut. Fills the gaps a newcomer falls into: commands, done criteria, the stops wanted, hazards, settled decisions. Re-points everything that cited the old text, and verifies with a fresh-context diff review and spot-tested tasks. User-invoked only.
- License
- Apache-2.0
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- trim-loop.md · references/
SKILL.md (first lines)
# Trim agent instructions
<run>
This skill is a standing prompt. The run is in
`${CLAUDE_SKILL_DIR}/references/trim-loop.md`. Read it now and execute it as
written: it is the instruction set for this run, not background.
</run>
<paths>
- AGENTS.md template: `${CLAUDE_PLUGIN_ROOT}/templates/AGENTS.md`
</paths>
<parameters>
Start from its `<parameters>` block and apply these overrides from the
invocation: $ARGUMENTS
An override that names no parameter goes under "Needs from me" rather than
being guessed into one.
</parameters>
<after_compaction>
Re-read the run file and your placement map before the next action. The run's
instructions do not survive compaction on their own, which is why the
placement map lives in a file.
</after_compaction>From fblissjr/fb-claude-skills, Apache-2.0.
More from fblissjr/fb-claude-skills
- 0.603score
heylook-provider
fblissjr
Wire an application to heylook (heylookitsanllm), a local multimodal LLM server on Apple Silicon serving MLX and gguf models over one Anthropic…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
skill-dashboard
fblissjr
Show an interactive dashboard of all tracked skills, plugins, and repo hygiene in this project.
SkillAFreshness: A★ 2Claude Code +9 - 0.563score
design-scoreboard
fblissjr
Designs what an improvement or optimizer loop should climb for a given project and goal, and what must not get worse while it does: goal metrics measured on…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
mece-decomposer
fblissjr
MECE decomposition methodology, scoring rubrics, and Agent SDK mapping for process analysis.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
python-tooling
fblissjr
House Python conventions plus the type-checking failures that get misdiagnosed: the dependency pinning policy (applications exact, libraries floors), the rule…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
dimensional-modeling
fblissjr
Design and implement Kimball-style star schemas in DuckDB for LLM agent state persistence.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
improve
fblissjr
Runs one improvement pass over a project in the direction its north star points, without breaking what it does today: faster in real use, less code, a truer…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
optimize
fblissjr
Speeds up a codebase as far as it will go in one session, against a hard target (every primary benchmark at least 1.2x faster than the base commit by default)…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
json-query
fblissjr
Guide JSON query tool selection and syntax.
SkillBFreshness: B★ 2Claude Code +9 - 0.558score
gemini-multimodal
fblissjr
Send a task to a Gemini model and get a structured answer back - perceptual work Claude cannot do directly, or any ad-hoc question worth a second model's take.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
retire
fblissjr
Remove a unit from a repo without leaving references behind - a plugin, package, module, directory, dependency, or feature.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
claim-audit
fblissjr
Audits prose as untrusted claims and re-derives each one by running a command, never by reading and nodding: the added lines of a diff, a standing doc such as…
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/fblissjr/fb-claude-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fblissjr
- 0.603score
heylook-provider
fblissjr
Wire an application to heylook (heylookitsanllm), a local multimodal LLM server on Apple Silicon serving MLX and gguf models over one Anthropic…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
skill-dashboard
fblissjr
Show an interactive dashboard of all tracked skills, plugins, and repo hygiene in this project.
SkillAFreshness: A★ 2Claude Code +9 - 0.563score
dimensional-modeling
fblissjr
Design and implement Kimball-style star schemas in DuckDB for LLM agent state persistence.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
mece-decomposer
fblissjr
MECE decomposition methodology, scoring rubrics, and Agent SDK mapping for process analysis.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
python-tooling
fblissjr
House Python conventions plus the type-checking failures that get misdiagnosed: the dependency pinning policy (applications exact, libraries floors), the rule…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
improve
fblissjr
Runs one improvement pass over a project in the direction its north star points, without breaking what it does today: faster in real use, less code, a truer…
SkillBFreshness: B★ 2Claude Code +9
Cite this page
trim-agents-md skill. Agent Mart. https://agentmart.dev/skills/fblissjr-trim-agents-md (last updated 2026-10-24)