chan4lk

chan4lk/specclaw

Plugin Claude Code

Claude Code plugins by chan4lk.

chan4lk/specclaw

Instructions file

Instructions for chan4lk/specclaw, covering git workflow, version bump rule, cloning additional repos, interactive progress reporting (required) and discord conventions.

chan4lk/specclaw

Plugin Claude Code

Spec-driven development framework for Claude Code. Manages the propose → plan → build → verify → pr lifecycle with structured proposals, specs, designs, task lists, and GitHub/Azure DevOps/Jira integrations.

chan4lk/specclaw

Agent

Reviews changed files for a specclaw change across 10 quality dimensions (correctness, security, YAGNI/simplicity, one-liner opportunities, naming, complexity, test quality, design adherence, scope creep, dead code). Produces review-report.md with BLOCK/WARN/NOTE findings and an…

chan4lk/specclaw

Agent

Party-mode panelist — structural fit. Attacks duplication of existing mechanisms, wrong seams, blast radius at merge time, under-specified contracts, and untestable designs. Read-only; returns findings as its final message. Seated at every tier.

chan4lk/specclaw

Agent

Party-mode panelist — problem fidelity. Attacks whether the proposal's stated problem is the real problem and whether its evidence is real. Read-only; returns findings as its final message. Seated at tier standard and above.

chan4lk/specclaw

Agent

Sizes the adversarial review panel for a specclaw proposal. Reads proposal.md and returns a JSON object with a depth tier (thin/standard/deep), domain flags, a one-sentence rationale, and three depth signals. Runs inside /specclaw:propose when party.enabled is true and no tier override is set; specclaw-party turns the…

chan4lk/specclaw

Agent

Party-mode panelist — value per token. Attacks scope size, cost, the cheapest variant that captures most of the value, the do-nothing option, and the shipped defaults. Read-only; returns findings as its final message. Seated at every tier.

chan4lk/specclaw

Agent

Party-mode panelist — trust boundaries and misfire behaviour. Attacks hostile input, fail-open failure modes, over-broad permissions, and irreversible runtime effects with no recovery path. Read-only; returns findings as its final message. Seated at tier deep or when a security domain flag is set.

chan4lk/specclaw

Agent

Party-mode panelist — the long horizon. Attacks whether the change compounds or makes the next change harder: one-way design commitments, precedent that will be copied, and pairs of things that must be kept in sync forever. Read-only; returns findings as its final message. Seated at tier deep.

chan4lk/specclaw

Agent

Interactively co-authors a high-quality spec.md for a specclaw change. Walks the user through the spec template section by section, applying named brainstorming techniques (5 Whys, Jobs-to-be-Done, Inversion, Pre-mortem, MoSCoW, Concrete-example probe) and challenging vague or untestable requirements before writing…

chan4lk/specclaw

Skill Claude CodeCodex

Move a completed change to .specclaw/changes/archive/ under its existing name. Closes the GitHub Issue (if sync is enabled) and optionally creates a git tag. Use after a change is merged — the PR is complete and the change should leave the active list.

chan4lk/specclaw

Skill Claude CodeCodex

Interactive setup for Azure DevOps authentication. Prompts for organization, project, and repo, validates a Personal Access Token, and saves credentials to gitignored .specclaw/.env. Run once per project before /specclaw:pr-azdo.

chan4lk/specclaw

Skill Claude CodeCodex

Interactive setup for Jira authentication. Prompts for domain, email, project key, and issue type, validates an Atlassian API token, and saves credentials. Run once per project before /specclaw:issue.

chan4lk/specclaw

Skill Claude CodeCodex

Interactively co-author spec.md for an approved proposal via the spec-author subagent. The agent walks the user through the spec template section by section, applying named brainstorming techniques (5 Whys, Jobs-to-be-Done, Inversion, Pre-mortem, MoSCoW) and challenging vague requirements. Use when you want a…

chan4lk/specclaw

Skill Claude CodeCodex

Run the propose → plan → build → verify lifecycle autonomously across the queue of active changes. Advanced — requires automation config in config.yaml. Use when you want specclaw to advance every change to its next phase without prompting; do not use for a single targeted change (use the specific verb instead).

chan4lk/specclaw

Skill Claude CodeCodex

Create or update an Azure Boards Work Item that mirrors this proposal. Targets Azure DevOps Boards (Features / User Stories / Tasks / Bugs / Epics) using the credentials from /specclaw:auth-azdo. Mirrors /specclaw:issue (Jira) and the GitHub Issues sync but for ADO Boards. Requires azdo.boards.sync: true in…

chan4lk/specclaw

Skill Claude CodeCodex

Manage the project's living context document (.specclaw/context.md). View, add, or edit project-level rules, patterns, coding style, and architecture decisions that all lifecycle skills load automatically. Use show to view, add to append a rule, edit to rewrite a section, reset to restore from template.

chan4lk/specclaw

Skill Claude CodeCodex

Initialize specclaw in this project. Creates the .specclaw/ directory, generates config.yaml from the template, and sets up the project dashboard. Run once per project before any other specclaw command.

chan4lk/specclaw

Skill Claude CodeCodex

Create a Jira issue for a proposed change. Mirrors GitHub Issues sync but for Jira-based teams. Builds the issue summary and description from proposal.md and spec.md. Requires credentials from /specclaw:auth-jira. Idempotent — warns if a Jira issue already exists for this change.

chan4lk/specclaw

Skill Claude CodeCodex

Record a build learning — a spec gap, design miss, recurring pattern, or insight discovered during implementation. Appends to .specclaw/changes/ /learnings.md. Use mid-build to capture knowledge before it's lost; do not use for routine progress updates.

chan4lk/specclaw

Skill Claude CodeCodex

Autonomously iterate build→verify→review until every gate is green or a guardrail halts. Drives the specclaw-loop controller — evaluate gates, reflect, fix the smallest diff, re-verify the whole change, and repeat. Use when asked to loop, iterate until done, or keep fixing until tests pass / verify passes / review is…

chan4lk/specclaw

Skill Claude CodeCodex

Inspect the cross-change pattern registry. Track recurring errors and learnings across changes; promote patterns with 3+ occurrences to prevention rules. Use to see what keeps happening before planning a new change.

chan4lk/specclaw

Skill Claude CodeCodex

Generate spec, design, and ordered task list for an approved proposal. Reads proposal.md, analyzes the codebase, then writes spec.md, design.md, and tasks.md. Run after /specclaw:propose has been approved, before /specclaw:build.