gauge
Skill2 starsChanged 31 days agoApache-2.0View on GitHub
Install or tune useful static feedback for a codebase and verify that it catches representative mistakes. Use for type-checking and lint feedback loops, not claims that static checks prove correctness.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- simota/agent-skillstheir own version, first seen Oct 23, 2026
- matthewharrilal/claude-skillstheir own version, first seen Oct 13, 2026
- olcayseygan/crumoratheir own version, first seen Oct 2, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- simota/agent-skills★ 96same name
- matthewharrilal/claude-skills★ 0same name
- olcayseygan/crumora★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- canonSkill
- colorSkill
- formSkill
- graphicsSkill
- layoutSkill
- motionSkill
- pilotSkill
- systemsSkill
- typeSkill
- holdfastSkill
- aegisSkill
- assaySkill
- flightlineSkill
- groundworkSkill
- gungnirSkill
- husbandrySkill
- load-bearingSkill
- pilotSkill
- plumbSkill
- stationkeepingSkill
- crucibleSkill
- envoySkill
- forgeSkill
- ledgerSkill
- prospectSkill
- reckoningSkill
- forageSkill
- touchstoneSkill
- bearingsSkill
- bulwarkSkill
- keelSkill
- liverySkill
- lookoutSkill
- pilotSkill
- seaworthySkill
- trialsSkill
- wellspringSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
Before starting, inspect the project and bind TYPECHECK_CMD to its real trusted command with --var 'TYPECHECK_CMD=<actual command>'.
- Distinctive: line 34
Read existing tool configuration and measure the present diagnostic baseline.
- Very specific: line 43
When this stage is fulfilled: checklist advance baseline --run "$RUN".
- Very specific: line 56
Run the bound sensor: checklist verify configure --run "$RUN".
- Very specific: line 57
Only if the check genuinely does not apply: checklist na configure static-checker-green --run "$RUN" --reason "<scope reason>".
- Distinctive: line 76
If adopting strict checks would bury the target work in unrelated errors, use a documented incremental boundary.
- Very specific: line 78
If an input or permission is missing, name the blocker and leave the relevant item pending.
- Very specific: line 84
After all required work and stage closures is recorded, use checklist done --run "$RUN".
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!--
Copyright 2026 IamK77 — Licensed under the Apache License, Version 2.0.
See ./LICENSE and ./NOTICE · https://www.apache.org/licenses/LICENSE-2.0
-->gauge
Install or tune useful static feedback for a codebase and verify that it catches representative mistakes. Use for type-checking and lint feedback loops, not claims that static checks prove correctness.
Inputs
Target language/toolchain; existing diagnostics and configuration; failures worth preventing; actual static-check command.
Run record
Use checklist 0.5 or newer for this SOP. Reading or reloading the skill must not reset work. For a new task, run checklist init "${CLAUDE_SKILL_DIR}" --new --path "/absolute/project"; retain its returned ID as RUN. For existing work, use checklist resume "$RUN", then checklist show --run "$RUN". Outside Claude, replace the skill-directory variable with this directory’s actual path.
Commands below record work after it is done. Replace evidence placeholders with concise artifact locations and observations. Manual confirmations are not independent proof; a sensor pass covers only the command and inputs it observed. verify does not close a stage; advance checks that its required readings are fulfilled. Use report --run "$RUN" for the retained history.
Before starting, inspect the project and bind TYPECHECK_CMD to its real trusted command with --var 'TYPECHECK_CMD=<actual command>'. Do not use an echo/no-op to produce a green result. checklist resume "$RUN" --var 'TYPECHECK_CMD=<new command>' changes the binding and invalidates earlier readings; commands and output are stored locally, so do not bind secrets.
Procedure
baseline
Read existing tool configuration and measure the present diagnostic baseline. Choose a feedback loop for errors that matter in this project, not a generic strictness score.
Record these artifacts after doing the work:
- Current configuration and diagnostic baseline are recorded.
checklist check baseline baseline --run "$RUN" --evidence "<artifact and observation>" - Target error classes and acceptable adoption scope are named.
checklist check baseline goal --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance baseline --run "$RUN".
configure
Make a focused configuration or typing change. Introduce a representative error, confirm the tool reports it, then restore the file and run the real check. Document suppressions individually.
Record these artifacts after doing the work:
- A representative mistake was detected and the probe restored.
checklist check configure sensitivity --run "$RUN" --evidence "<artifact and observation>" - New suppressions or exclusions have explicit reasons.
checklist check configure exceptions --run "$RUN" --evidence "<artifact and observation>"
Run the bound sensor: checklist verify configure --run "$RUN". A failed or unavailable command is not a successful review.
Only if the check genuinely does not apply: checklist na configure static-checker-green --run "$RUN" --reason "<scope reason>". N/A stays distinct from pass.
When this stage is fulfilled: checklist advance configure --run "$RUN".
handoff
Connect the same command to the developer workflow or CI when requested. Explain which runtime behaviours still need tests.
Record these artifacts after doing the work:
- Reproducible invocation and integration location are documented.
checklist check handoff workflow --run "$RUN" --evidence "<artifact and observation>" - Static guarantees and unchecked runtime behaviour are distinguished.
checklist check handoff ceiling --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance handoff --run "$RUN".
Branches
If adopting strict checks would bury the target work in unrelated errors, use a documented incremental boundary. An unavailable tool is an error or an explicit N/A, never a green check.
If an input or permission is missing, name the blocker and leave the relevant item pending. A changed requirement may need a new run; an accepted checklist edit uses resume "$RUN" --refresh and requires fresh readings. To abandon work, use checklist reset --run "$RUN" --reason "<reason>"; history is retained.
Completion
A working feedback loop with demonstrated sensitivity and a documented ceiling. Assay covers behavioural claims that static feedback cannot establish.
After all required work and stage closures is recorded, use checklist done --run "$RUN". This archives the result without deleting its history; it does not authorise any external action.
Reference shelf
Open the technique relevant to the current step. These notes provide concrete methods and examples, not additional phases; this entrypoint defines the run's completion conditions.
- Designing a useful feedback loop
- Choose a feedback source for a specific mistake
- Combine observations without confusing their scope
- State what a static check actually establishes
- A Python feedback loop that fits the project
- A TypeScript feedback loop that reaches consumers
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.