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
95Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

adversarial-review

02

Eliyce/paqad-ai

Skill Codex

Perform rigorous, risk-first review after design and implementation.

not rated 8 yesterday A 16 tokens original MIT

Eliyce/paqad-ai

Skill Codex

When the analyticsinstrumentation flag is on and the classify-time gate resolved to instrument, this skill wires a feature's analytics the tracking-plan-as-code way (issue.

not rated 8 yesterday A 41 tokens original MIT

api-doc-maintainer

04

Eliyce/paqad-ai

Skill Codex

Maintains per-module API documentation after endpoint changes.

not rated 8 yesterday A 14 tokens original MIT

canonical-doc-sync

05

Eliyce/paqad-ai

Skill Codex

Synchronize implementation changes back into canonical documentation.

not rated 8 yesterday A 13 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Estimate the implementation phase's token footprint from spec, test plan, and affected files; recommend compaction before context starvation.

not rated 8 yesterday A 29 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Pre-implementation scan that classifies how a proposed change affects each consuming module's public surface and recommends coordinated changes.

not rated 8 yesterday A 29 tokens original MIT

decision

08

Eliyce/paqad-ai

Skill Codex

Authors the small, human-facing Decision Pause packet described by the Decision Pause Contract (in the framework bootstrap AGENT-BOOTSTRAP.md) without the agent hand-authoring the id, timestamps, or JSON. create mints a collision-free D- id and writes the pending packet; resolve records the chosen option and rationale…

not rated 8 yesterday A SkillSpector: pass 103 tokens original MIT

diff-doc-sync

09

Eliyce/paqad-ai

Skill Codex

Identify only the canonical docs made stale by the current diff.

not rated 8 yesterday A 16 tokens original MIT

diff-minimizer

10

Eliyce/paqad-ai

Skill Codex

Classify each proposed implementation step against the acceptance criteria so scaffolding and over-build are dropped before code is written.

not rated 8 yesterday A 28 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Canonical orchestrator that runs the fast stale-doc detector and dispatches to per-domain doc-sync skills for the affected canonical paths.

not rated 8 yesterday A 29 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Run the post-onboarding documentation creation workflow using the canonical tracker and the current application manifests. Supports two stages — foundation (docs/instructions/ and module-map.yml) and module-docs (docs/modules/ from reviewed map).

not rated 8 yesterday A SkillSpector: pass 49 tokens original MIT

edge-case-detection

13

Eliyce/paqad-ai

Skill Codex

Identify failure modes and uncommon but relevant paths.

not rated 8 yesterday A 14 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Inspect canonical docs and registries before new artifacts are written.

not rated 8 yesterday A 17 tokens original MIT

finding-normalizer

16

Eliyce/paqad-ai

Skill Codex

Convert heterogeneous security evidence into stable pentest finding entries.

not rated 8 yesterday A 15 tokens original MIT

glossary-maintainer

17

Eliyce/paqad-ai

Skill Codex

Maintain shared business terminology in the glossary.

not rated 8 yesterday A 14 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Run the deterministic module-attribution extractor over a user prompt and surface any MD-XXXX drafts via the Decision Pause Contract. This is the first half of the Attribution Gate spliced into feature-development.planning (issue.

not rated 8 yesterday A SkillSpector: pass 48 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Form a hypothesis about which existing module a user prompt belongs to when the deterministic extractor returns nothing. Reads existing module-map.yml features and source paths, scores token overlap, returns a ranked multi-choice draft, and surfaces it via the Decision Pause Contract. Second half of the Attribution…

not rated 8 yesterday A SkillSpector: warn 64 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Test-driven module-health rollup. Issue.

not rated 8 yesterday A SkillSpector: warn 13 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Whole-project module-health refresh. The agent-facing "update module health" workflow. Runs the test-driven rollup (coverage / tests / changevelocity from the active stack pack's declared reports) and then the session-evidence sync (defect frequency / contract stability / verification status) across every declared…

not rated 8 yesterday A SkillSpector: warn 149 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Retrospective reconciler that scans the source tree against module-map.yml and docs/modules/, emits MM- findings into .paqad/module-map/drift.json, and surfaces user-approvable deltas. Issue.

not rated 8 yesterday A SkillSpector: warn 49 tokens original MIT

Eliyce/paqad-ai

Skill Codex

Identify performance hazards in a proposed solution or change set before code is written, classified by severity and hot-path placement.

not rated 8 yesterday A 29 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: