Eliyce/paqad-ai

Spec-driven development framework — AI agents that think before they type

This repository also configures its own agents. See what paqad-ai tells them →

8Stars on the repository
98Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

index-optimization

49

Eliyce/paqad-ai

Skill Codex

Review and improve indexing strategy for changed data paths.

not rated 8 today A 14 tokens original MIT

journey-synthesis

50

Eliyce/paqad-ai

Skill Codex

Propose a small set of capped, well-formed journeys over the verified map — one actor, one goal, ordered evidenced steps, dual ends — all marked proposed for human confirmation, never auto-confirmed.

not rated 8 today A 47 tokens original MIT

map-verification

51

Eliyce/paqad-ai

Skill Codex

Adversarially refute or confirm the claims the deterministic checks could not settle — the Tier-B pass over the site map — grounding each verdict in resolving evidence and never rubber-stamping.

not rated 8 today A 42 tokens original MIT

motion-review

52

Eliyce/paqad-ai

Skill Codex

Verify animations match motion.md budgets and prefers-reduced-motion is respected.

not rated 8 today A 17 tokens original MIT

responsive-review

54

Eliyce/paqad-ai

Skill Codex

Verify declared breakpoints are exercised, no horizontal scroll appears, touch targets meet spec, and RTL parity holds when declared.

not rated 8 today A 27 tokens original MIT

root-cause-analysis

55

Eliyce/paqad-ai

Skill Codex

Generate a canonical RCA artifact for an incident or failure.

not rated 8 today A 16 tokens original MIT

site-map-assembly

56

Eliyce/paqad-ai

Skill Codex

Drive the compile verb that folds the surface, transition, and guard layers into app-map.yaml, and resolve merge conflicts against the locked committed content without overwriting curated entries.

not rated 8 today A 39 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Turn the graph invariants and verification verdicts into stable SM- findings and a gap report, so the map's problems are triaged, evidenced, and each carry a concrete fix.

not rated 8 today A 42 tokens original MIT

site-map-maintainer

58

Eliyce/paqad-ai

Skill Codex

Keep the site map fresh during a feature-development change — when a diff touches flow-relevant files, patch just the affected surfaces so the map never drifts from the code it describes.

not rated 8 today A 42 tokens original MIT

site-map-readiness

59

Eliyce/paqad-ai

Skill Codex

Grade whether the project is mappable — app kind, frameworks, and an extractor that covers its shape — and route the unmappable case before any other site-map skill runs.

not rated 8 today A 40 tokens original MIT

site-map-retest

60

Eliyce/paqad-ai

Skill Codex

Re-check the stored site map against the current code by running the same verification again — never invent a finding, never soften one, never call the absence of proof a fix.

not rated 8 today A 40 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Verify every component in the AST inventory implements its declared states (default/hover/focus/disabled/loading/error/empty) and is exercised by Playwright tests.

not rated 8 today A 37 tokens original MIT

surface-extraction

62

Eliyce/paqad-ai

Skill Codex

Run the extractors, normalize the raw surfaces, and fingerprint the result so the site-map run has a deterministic, evidence-backed inventory of what the app exposes.

not rated 8 today A 36 tokens original MIT

surface-modeling

63

Eliyce/paqad-ai

Skill Codex

Turn raw extracted surfaces into named, typed, module-attributed surfaces with entry and exit marks — the non-inferable layer the engine cannot derive from the code alone.

not rated 8 today A 38 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Detect hard-coded design values (hex, raw px/rem, ad-hoc font stacks) in UI source that should resolve to a declared token. High severity by default.

not rated 8 today A 39 tokens original MIT

transition-tracing

65

Eliyce/paqad-ai

Skill Codex

Find and evidence the transitions between surfaces — where navigation actually goes, what triggers it, and the file:line that proves it — without inventing edges from mere links.

not rated 8 today A 38 tokens original MIT

ui-doc-maintainer

66

Eliyce/paqad-ai

Skill Codex

Maintain UI screens, components, and state docs after UI changes.

not rated 8 today A 18 tokens original MIT

ux-design-research

68

Eliyce/paqad-ai

Skill Codex

Research external UI references for full-lane UI work.

not rated 8 today A 16 tokens original MIT

ux-state-machine

70

Eliyce/paqad-ai

Skill Codex

Define interface states and transitions for UI-heavy work.

not rated 8 today A 14 tokens original MIT

content-planner

72

Eliyce/paqad-ai

Skill Claude CodeCodex

Shape a writing task into an outline, brief, sequence, or publishable plan. Use when a content request needs structure (audience, goal, outline, success metric) before drafting.

not rated 8 today A 42 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: