All authors
donald-ada avatar

Claude Skills by donald-ada

github.com/donald-ada
23 skillsA× 230 installs0 views
ArchitectA

Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — stress-tested against the field, its consequences confirmed by the user. A command the user types, for greenfield or architecture-shaping work; standalone, no other skill required.

ai-agentsgoapi
0
6
BlindspotA

Find the unknowns before they find the work — a read-only territory pass that surfaces the questions nobody knew to ask, judgment taught before a choice is extracted, and a quiz that catches the user's map up with what actually changed. Use when work enters territory the user calls unfamiliar, when the user is confirming a choice they can't evaluate, or when the user asks what they're missing or wants to be quizzed before accepting built work.

ai-agentsgoapi
0
6
CompactA

Put the compaction question to a snapshot that drifted — route what no longer constrains unfinished work, and say what moves before moving it. In flight or done; the log is appended to, never edited or trimmed.

ai-agentsgo
0
6
Decision RecordA

Keep the index of the project's settled decisions in .genius/DECIDED.md — one line per decision, pointing at the fight that settled it, earned by one test: would a future stranger re-fight this? Use when such a decision lands, when a design might contradict a settled one, or when another skill needs the index discipline.

ai-agentssql
0
6
DesignerA

Settle the look before the pixels — name the base and the delta, settle taste by looking, commit one design language to DESIGN.md. A command the user types, for work with an interface someone will see; standalone, no other skill required.

ai-agentsgit
0
6
DiagnoseA

Debugging as the six geniuses at minute scale — the bug confirmed by a red reproduction before any theory, hypotheses plural with kill-reasons before any fix, the fix proven by a fresh green rerun. Use when something is broken, throwing, failing, flaky, or slow, or when the user asks to debug or diagnose.

ai-agentsgotesting
0
6
DiscernA

Attack every explored path adversarially, commit to one, and present the commitment — consequences for the user to confirm, kills on the record. Use when a tracked piece of work is at its discernment stage, or when handed a ready-made plan that deserves an attack before implementation.

ai-agentsgo
0
6
DistillA

Retroactively distill the logs of finished work — delete what the repo now answers, keep what code cannot say. Done work only; in-flight logs are never touched.

ai-agentsgo
0
6
Domain GlossaryA

Maintain the project's shared vocabulary in CONTEXT.md — challenge conflicting terms, sharpen fuzzy language, record resolutions inline. Use when a term conflicts with or is missing from the glossary, when a decision names a new concept, or when another skill needs the glossary discipline.

ai-agentsgoapi
0
6
EnableA

Build one slice at a time with red-before-green tests at the agreed seams, tight feedback loops, and fresh-eyes review at every slice close. Use when a tracked piece of work is at its enablement stage and a slice needs building.

ai-agentsrustgo
0
6
ErrataA

Correct what was written wrong — the binding line rewritten in place, the record it came from appended to and never touched, both carrying the evidence that overturned it. Use when a run, a file, or the user contradicts something already written in a work file, a plan's contract, the glossary, or the decision index; when a pinned value or a stated fact turns out not to hold; or when another skill needs the correction discipline.

ai-agentsgo
0
6
GalvanizeA

Turn the chosen design into mobilized work — a brief, vertical slices with acceptance criteria, and agreed test seams. Use when a tracked piece of work is at its galvanizing stage.

ai-agentsgoexpress
0
6
Genius FileA

Read and update Working Genius work files — the work's folder holding the bounded snapshot a cold session acts on, the append-only log behind it, and the contract that binds the unbuilt slices. Use when a stage skill needs the work-file discipline, when the user asks what work is in flight or where a piece of work left off, or before resuming any work tracked under .genius/.

ai-agentsgoaws
0
6
GeniusA

The map of the Working Genius workflow — where each piece of work stands, what to run next, and where genius gaps are hiding.

ai-agentsgo
0
6
InventA

Genuinely explore structurally different approaches before committing — the alternatives exist to be beaten, not to be presented. Use when a tracked piece of work is at its invention stage.

ai-agentsrust
0
6
MigrateA

Move an in-flight two-file work into the folder layout — snapshot, log and artifacts into .genius/<slug>/, the contract out into CONTRACT.md, every link rebased. In-flight only; finished work is never converted.

ai-agentsgogit
0
6
ReconcileA

Check the project's binding documents against the repo they describe — settled decisions, glossary terms, pinned commands, in-flight plan contracts, the links between file and record — and route every drift to its correction.

ai-agentsgo
0
6
Record ProseA

How the flow's records are written — every document under .genius/, snapshot to backlog line. Use when writing or rewriting any of them, or when another skill needs the prose discipline.

ai-agentsgotesting
0
6
Setup Working GeniusA

Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.

ai-agentsgotesting
0
6
TenacityA

Drive the work to actually-done — fresh verification of every claim, context-isolated diff review, cleanup, commit, post-mortem. Use when a tracked piece of work is ready to close out, whether it moved through slices or was built directly after Wonder without them.

ai-agentsgogit
0
6
TriageA

Put the backlog's own rules to the backlog — seeds that should no longer be there, pairs that are one discovery, seeds that outgrew a line, and the order nobody has stated. Judged one at a time, landed only by the user's call.

ai-agentsgo
0
6
WaitwhatA

Re-explain what was just said for a reader who got lost — missing premises added, plain language, the project's own vocabulary, and one closing check that the repair landed. User-invoked only; only the reader knows when understanding broke.

ai-agentsgo
0
6
WonderA

Question the work before doing it — the interview that turns a raw idea into a confirmed problem statement. Use when a tracked piece of work is at its wonder stage, or when the user asks to start the Working Genius flow — or to be questioned — on a new idea. An ordinary request to build something is not an invitation to start the flow.

ai-agentsgo
0
6