Skip to content

Skills

The 53 skills we author, grouped by what you reach for them to do — the directory name is the command you type.

Plan & decide
Shape and pressure-test an idea before any code — widen the options, judge whether it's worth doing, and red-team the thinking.
brainstorm
standalonewriteshands-on

Use when a fuzzy idea needs shaping into a spec before any code

Read more
check-reasoning
checkreadhands-off

Use when a plan or diff needs red-teaming before you commit

Read more
grill-me
grillreadhands-on

Use when you want a plan stress-tested by interview

Read more
grill-with-docs
grillwriteshands-on

Use when you want a plan tested against your domain docs + the docs updated

Read more
ideate
standalonereadhands-off

Use when you want the options widened on a named problem

Read more
vet
standalonereadhands-off

Use when you're unsure an idea or tool is worth adopting — and where it belongs

Read more
wayfinder
standalone

(from mattpocock/skills v1.1, kept close to upstream as an experiment) Plan a chunk of work too big for one agent session as a shared map on GitHub — a `wayfinder:map` issue with child investigation tickets, native blocking edges, and a fog-of-war "Not yet specified" section — then resolve ONE ticket per session until the way to the destination is clear. Use to try the wayfinding flow on a big, fuzzy, multi-session effort. NOT brainstorm (single-flow double diamond → spec) · NOT organise (places the existing backlog) — this charts decisions still in fog.

Read more
Backlog
Turn plans into typed issues, classify them for readiness, place them into epics/sprints/milestones, and see what's next.
build-dev-plan
buildwriteshands-off

Use when you want to see what to work on next

Read more
find-untracked-work
findwriteshands-off

Use when you want built-or-intended work that isn't tracked surfaced

Read more
organise
standalonewriteshands-on

Use when issues need placing and ordering into epics / sprints / milestones

Read more
to-blog-issue
to

Capture a blog-post idea as ONE GitHub issue labelled `Blog post` — a braindump an agent later drafts from in the house voice. Files one backlog issue: the angle, why it matters, points to cover, source material. Surface-then-confirm before filing. Use for "this could make a good blog post", "blog this", "capture a blog idea". NOT to-tickets (a typed tree of build slices); NOT a drafting step (the post is written later, from the issue).

Read more
to-tickets
towriteshands-off

Use when a plan needs breaking into typed, grabbable issues

Read more
triage
standalonewriteshands-off

Use when an incoming issue needs a readiness status + area

Read more
Build
Execute the work — scaffold features and skills, and run sprints and epics one gated commit at a time.
build-claude-skill
buildwriteshands-on

Use when you're adding or renaming a skill

Read more
build-crud-in-tempo
buildwriteseither

Use when you're adding a DB-backed CRUD feature

Read more
build-epic
buildwriteseither

Use when you want to build a whole epic, sprint by sprint

Read more
build-helper-step-in-tempo
buildwriteseither

Use when you're adding a Task Helper enricher or refiner

Read more
build-sprint
buildwriteseither

Use when you want to plan then build out a sprint's issues

Read more
Ship & review
Get changes out the door — plan and action the open-PR stack, and roll one review nit out everywhere it occurs.
build-from-qa-plan
buildwriteshands-on

Use when you want the doable items off a QA plan actioned

Read more
build-pr-feedback
buildwriteshands-on

Use when you want one review nit applied everywhere it occurs

Read more
build-qa-plan
buildwriteshands-off

Use when you want the open PRs for a sprint or epic planned

Read more
Verify & QA
Prove a change is right before it ships — find missing tests, check conformance, root-cause bugs, and hunt vulnerabilities.
check-everything
checkwriteshands-on

Use when you want a full health sweep of your current change

Read more
debug
standalonewriteseither

Use when you're stuck on a reproducible bug

Read more
exterminate
standalonewriteshands-off

Use when you want the bug backlog cleared autonomously

Read more
find-vulns
findreadhands-off

Use when you want a security sweep of existing code

Read more
preflight
standalone

The make-green loop — run ci:check, fix, re-run, then chase mutation survivors — is the noisiest churn in a session and it floods your context. This runs the whole loop in an isolated fork and hands back one verdict, fixing the mechanical failures itself and flagging only the real decisions, so the thrash never reaches your thread.

Read more
qa-code
qareadhands-off

Use when a diff needs checking against our rules + architecture

Read more
qa-everything
qareadhands-off

Use when you want every QA pass run over a change at once

Read more
qa-mutants
qawriteshands-off

Use when surviving mutants need closing with real tests

Read more
qa-prompts
qareadhands-off

Use when a prompt needs auditing for gaps + failure modes

Read more
qa-tests
qareadhands-off

Use when you want missing test cases found before a PR

Read more
qa-ui
qawriteshands-off

Use when a UI page needs its quality + test coverage checked

Read more
Optimise
Make an existing thing faster or leaner without changing what it does — code, CI, prompts, the always-on context.
optimise-ci
optimisewriteshands-on

Use when CI is slow or expensive and needs trimming

Read more
optimise-code
optimisewriteshands-on

Use when a hot path is slow or heavy

Read more
optimise-context
optimisewriteshands-on

Use when the always-on context is bloated

Read more
optimise-prompts
optimisewriteshands-on

Use when a prompt is bloated and needs tightening

Read more
Harness care
Keep the harness itself healthy — audit the skill set and the whole system, measure whether a skill does what it promises, reconcile the docs, capture learnings, and source improvements.
eval
standalone

Changing a skill or mode used to be a vibes call — a tweak that looked better might silently regress a rule, like caveman dropping issue-links under compression. This runs a harness eval for one skill: control-vs-treatment sub-agents over its co-located eval set, blind-graded against a weighted rubric, reporting the delta and a hard PASS/FAIL on the leak-canary and link guards — so a change is measured, not guessed.

Read more
find-harness-improvements
findreadhands-off

Use when you want ideas to improve the whole harness

Read more
find-learnings
findwriteshands-on

Use when you just solved something worth remembering

Read more
qa-harness
qareadhands-off

Use when you want the whole harness audited as a system

Read more
qa-philosophy
qareadhands-off

Use when you want the docs reconciled against the code

Read more
qa-skills
qareadhands-off

Use when you want the skill set audited for dupes / dead skills

Read more
qa-wiki
qawriteshands-on

Use when the wiki has drifted from the harness

Read more
source-a-skill
sourcewriteshands-off

Use when you know exactly which capability you need

Read more
Ways of working
Standing manners that change how the agent works for a whole stretch, not one-off actions.
be-caveman
bemanner

Use when you want terse, low-token replies

Read more
be-complete
bemanner

Use when you want the whole change built — no stubs

Read more
be-radical
bemanner

Use when you want the harness's assumptions challenged

Read more
be-teacher
bemanner

Use when you want to understand it, not just get a diff

Read more
Housekeeping & reference
Tidy-ups and reference — repo cleanup, end-of-session wrap-up, session transcripts, the domain conventions, and frontend design taste.
build-transcript
buildreadhands-off

Use when you want this session exported for analysis or learning

Read more
design-taste-frontend
designwriteseither

Use when you're building a frontend that mustn't look templated

Read more
fyi-tempo-domain
fyiread

Use when you're working on Tempo's task / Todoist domain

Read more
janitor
standalonewriteshands-on

Use when merged branches, junk files or stale issues are piling up

Read more
wrap-up
wrapwriteshands-on

Use when you're ending a session and want loose ends tied off

Read more