technical-writing
Skill3 starsChanged 7 days agoMITView on GitHub
Flag a PR that ships a new env var, CLI flag, config key, exported function/type, or endpoint with no matching doc or changelog entry — working and undocumented, not broken. Apply to any addition, a new capability with no removal or behavior change to existing surface. Not for a reversed or superseded value (see retiring-a-superseded-decision) or a breaking API change (see api-contract-enforcement); pairs with the latter when a finding also touches behavior.
142 other projects use a version of this.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Nov 8, 2026
- Loner1024/skillstheir own version, first seen Nov 8, 2026
- lklimek/claudiustheir own version, first seen Nov 8, 2026
- justinyoo/skillstheir own version, first seen Nov 8, 2026
- metraton/gaiatheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ketchup-video, principle-explain-the-number and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
tristanphvnSkillketchup-video
Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.
Also in 14 projects that use this
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 29 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 20 projects that use this
jaydubya818Skillprinciple-attack-the-premise
Apply when repeated fixes fail and a shared assumption may be wrong.
Also in 35 projects that use this
jaydubya818Skillprinciple-test-behavior-not-implementation
Apply when tests mirror internals instead of asserting observable outcomes.
Also in 36 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
- +5 more from jaydubya818
Other versions142 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 142
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- vercel/eve★ 5.8ksame name
- backnotprop/pstack★ 3.8ksame name
- chattocorp/chatto★ 2.9ksame name
- cashew-labs/libretto★ 898same name
- saffron-health/libretto★ 883same name
- moeru-ai/xsai★ 667same name
- proffesor-for-testing/agentic-qe★ 524same name
- NPC-Worldwide/npcsh★ 502same name
132 more not listed
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 repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- clud-bug-collaborationSkill
- critical-issues-onlySkill
- evidence-based-reviewSkill
- respect-existing-conventionsSkill
- skill-frontmatter-qualitySkill
- apca-contrastSkill
- api-contract-enforcementSkill
- brand-voice-reviewSkill
- chroma-harmonizationSkill
- clud-bug-collaborationSkill
- component-sizing-principlesSkill
- component-sizingSkill
- composing-a-screenSkill
- consuming-a-design-systemSkill
- conventions-templateSkill
- critical-issues-onlySkill
- curating-a-skill-catalogSkill
- designing-a-design-systemSkill
- designing-elite-uiSkill
- design-system-consistencySkill
- design-token-namingSkill
- dtcg-formatSkill
- empirical-design-principlesSkill
- evidence-based-reviewSkill
- finding-a-catalog-skillSkill
- frontend-a11ySkill
- guarding-a-regressionSkill
- ios-safari-surfacesSkill
- line-height-gridSkill
- logmindSkill
- motion-continuitySkill
- oklch-color-spaceSkill
- orchestrating-agent-delegationSkill
- orchestrating-a-multi-agent-runSkill
- orchestrating-elite-agent-qaSkill
- palette-relationshipsSkill
- pii-and-complianceSkill
- proving-an-absenceSkill
- respect-existing-conventionsSkill
- retiring-a-superseded-decisionSkill
- reviewing-design-workSkill
- semver-design-tokensSkill
- session-heartbeatSkill
- skillforgeSkill
- skill-frontmatter-qualitySkill
- spacing-systemSkill
- test-disciplineSkill
- thrill-designSkill
- token-frugal-toolingSkill
- token-naming-conventionsSkill
- type-scaleSkill
- udts-component-sizing-laddersSkill
- udts-dtcg-extensionsSkill
- udts-linter-rulesSkill
- udts-naming-conventionSkill
- udts-reviewSkill
- udts-semver-defaultsSkill
- udts-spacing-defaultsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 134 edited versions we read keep these.
1
Distinctive
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
- Distinctive: line 82
If the finding also touches the diff's behavior, pair it with the code-aware skill that owns that surface.
- Very specific: line 99
Keep a Changelog 1.1.0, keepachangelog.com — the Unreleased section and the Added/Changed/Deprecated/Removed/Fixed/Security categories.
“Common” is measured: kept by at least 6 in 10 of the 134 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
Technical writing
A shipped addition and its documentation are two separate facts, and only one
is checked by CI. check-doc-links.yml proves links resolve; check-prose-
retention.yml stops prose disappearing unannounced. Neither asks whether a
new env var, flag or export has a matching line anywhere — both are built to
catch loss, not silence, and an addition is not a loss. The clud-bug seed
(CLUD_BUG_NOTARY_URL, --bundle) shipped working and undocumented; this
repo's own bd1b554/8f7fdbb F2 pass existed to close the same gap a second
time, independently. Two occurrences is a pattern, not a one-off.
When to use
- A diff adds a new env var, CLI flag, config key, exported function/type, or endpoint that runs correctly and ships with no doc or changelog line naming it.
- You are closing a "docs truth" pass and need to confirm every addition since the last one is covered — not just that the existing docs still resolve.
- A PR's own description claims a capability the diff adds, but no README,
--helptext, docstring or CHANGELOG entry says so anywhere in the tree.
When NOT to use
- The change reverses an earlier value.
retiring-a-superseded-decisionowns this, and says why it doesn't cover the addition case: "The decision is new and replaces nothing — no old value to hunt." An addition has no old value by definition — that gap is this skill's case, not that one's. - The change breaks an existing surface.
api-contract-enforcementowns removed fields, renamed parameters, changed status codes, tightened validation — and disclaims itself only where "the change is purely additive — adding a new optional field, new endpoint, new CLI flag — with no removal or behavior change to existing surface," which is precisely this skill's territory, not its own. - The finding is about the diff's behavior, not its documentation. This is
a
kind: writingskill; per SPEC §2.2 it must not be the sole citation for a claim about code behavior — pair it with theruleskill that owns that surface (oftenapi-contract-enforcement) when the code itself, not only its coverage, is in question.
Search the new surface, not the old one
An addition has nothing to contradict, so there is no stale sentence to find —
the failure mode is a gap, not a lie, and the thing to search for is the new
name itself: the flag's own spelling, the env var's own spelling, the export's
own spelling, across every doc location (README, CHANGELOG, --help text,
docstrings). A hit is coverage; nothing is the finding. Control-test the search
first against an addition you already know is documented, per
proving-an-absence — a search that finds nothing may be the search, not the
repo.
Changelog cadence
The same PR that ships the capability states what changed, in the format its
readers use — not a promised follow-up. SemVer ties this to a version-visible
fact: "MINOR version when you add functionality in a backward compatible
manner" (semver.org §7–8). Keep a Changelog is one worked instantiation of the
cadence itself: an Unreleased section at the top, entries grouped by type
(Added/Changed/Deprecated/Removed/Fixed/Security), one section per
version. Two named systems make the rule machine-checkable instead of a habit
to remember: Changesets gates a merge on changeset status --since=main
failing when code changed with no changeset file; towncrier requires one
newsfragment file per PR, assembled into the changelog at release. Neither is
prescribed here — the generic rule is that the PR adding the surface also
states it; which mechanism enforces that is the repo's own choice.
Verification
- Grep the new surface's own name across doc locations; control-test against a known-documented addition first, so a broken search doesn't read as a clean repo.
- Confirm the changelog entry (or the repo's chosen mechanism) landed in the same PR — not a promise to add it later.
- If the finding also touches the diff's behavior, pair it with the code-aware skill that owns that surface; this skill's citation alone does not cover a behavior claim.
Cross-references
- retiring-a-superseded-decision — the reversed-value case this skill excludes; search the old value, not the new one.
- api-contract-enforcement — the breaking-change case this skill excludes; pair with it when a finding also touches behavior, per SPEC §2.2.
- proving-an-absence — control-testing the "no doc found" grep before reporting it.
Sources
- Keep a Changelog 1.1.0, keepachangelog.com — the
Unreleasedsection and theAdded/Changed/Deprecated/Removed/Fixed/Securitycategories. - Semantic Versioning 2.0.0 §7–8, semver.org — MINOR for backward-compatible additions.
- Changesets, github.com/changesets/changesets
docs/automating-changesets.md—changeset status --sinceas a merge-time gate. - towncrier, github.com/twisted/towncrier — one newsfragment file per PR.
- protocol SPEC §2.2, github.com/thrillmade/protocol
SPEC.md—kindroutes a skill to a pass; the pairing rule this skill'skind: writingis bound by.
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.

