agentleFS
Sign inStart free
darellchua2darellchua2/civiltekk-opencode-claude-skills/skills/linting-inline-skill/SKILL.md

linting-inline-skill

Skill7 starsChanged 56 days agoApache-2.0View on GitHub

In-session linting delegate — discovers the language linter, runs it scoped to touched files only, applies gate semantics from verification-loop-skill, and fixes or reports findings inline. Decision tree with skip rules, scope bounds, enforcement deltas, and output contract. Triggers: inline lint, lint in-session, plan-execution-inline-skill linting step.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Skip check: no linter configured for the changed languages (no eslint/ ruff/checkstyle/dotnet-format configs, no manifest scripts) → report …

    line 24
  2. Distinctive:

    No config changes (adding plugins, disabling rules) — that is a finding.

    line 42

≈ “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

Linting (inline)

You are executing the linting delegate's workflow in this session. The subagent's isolation (fresh context, sandbox, tier model) is replaced by the discipline below — advisory, but the gate's verdict depends on it.

Decision tree

  1. Skip check: no linter configured for the changed languages (no eslint/ ruff/checkstyle/dotnet-format configs, no manifest scripts) → report "lint-inviable", stop. Never add a linter config unprompted.
  2. Discover: linter + invocation from manifests/config per language-linting-skill (Ruff for Python, ESLint for TS/JS, Checkstyle/ SpotBugs for Java, dotnet format for C#). Autoloaded by that skill where available.
  3. Scope (scoped-lint rule): lint ONLY the files in the current diff (git diff --name-only --diff-filter=AM). Full-suite lint is the gate's job, not yours.
  4. Gate semantics per verification-loop-skill: auto-fixable → fix and re-run once; remaining findings → report by severity with file:line.
  5. INCONCLUSIVE (linter crashes, config broken) → report it as such; never declare green without a run.

Scope bounds

  • Fixes touch only the linted files and only the flagged findings.
  • No config changes (adding plugins, disabling rules) — that is a finding.

Enforcement deltas (vs linting-subagent)

Subagent enforcementInline discipline (you)
Fresh context windowState the touched-file list before linting so scope drift is visible
Isolated fix sandboxFixes land in the working tree directly — list every file you changed in Output
Tier modelSame model as the caller — flag uncertainty instead of suppressing findings

Output contract

Status: [success | partial | failed | inconclusive] Output: linter(s) run + files linted + findings (fixed vs reported, file:line) Summary: ≤3 sentences Issues: unfixable findings, config problems, or "None"

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.

Check your setup, free