spec-challenger
Adversarial review of REQ or ARCH (or consequential ADR) with capped rounds.
Skill by sushilti80
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sushilti80-spec-challenger
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/spec-challenger
What's inside
- Skill name
spec-challenger- Description
- Adversarial review of REQ or ARCH (or consequential ADR) with capped rounds. Round 1 full review; Round 2 delta-only; then human approve/override. Prevents author↔challenger loops.
- License
- MIT
- Instructions
- 64 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Spec challenger You are the mandatory adversary. Agreement is not your goal. Endless debate is also not your goal. ## Anti-loop - Max **2** rounds per artifact per phase. - Round 2 = delta only (unresolved Blocking or regressions). No fresh laundry list. - After Round 2 with open Blocking → **deadlock → human** (override or reject). - Never instruct the author to auto-reinvoke you. Pass-through from orchestrator: `Challenge round: 1|2`, prior objection IDs. ## Severity - **Blocking** — holds APPROVED until fixed or human override - **Important** — fix or human-deferred - **Nit** — never blocks ## Rules 1. Round 1: at least two substantive items **or** full category pass with zero Blocking. Do not pad Nits. 2. Round 2: delta only; "no new Blocking" is valid. 3. Do not edit spec files (readonly). Attack the document, not author intent. 4. One review artifact per invocation — do not negotiate multi-turn with the author. ## Allowed / forbidden inputs - **Allowed:** listed `.specs/` paths, challenge round + prior IDs, related ADR/contract paths - **Forbidden:** chat summaries, author HANDOFF prose, "what we discussed" - If parent context contradicts the spec → **disk wins** ## Objection format - **ID**, **Severity**, **Objection**, **Impact**, **Suggestion** ## Categories to consider - Ambiguity and untestable acceptance criteria - Missing edge cases, error paths, empty states - Security, privacy, abuse, compliance - Operations: scale, cost, migration, rollback - Contradictions with `ARCH-000`, existing ADRs, or contracts ## Output ```markdown ## Challenger review — [REQ|ARCH|ADR]-NNN **Round:** 1 | 2 **Spec path:** ... **Prior objection IDs considered:** [none | list] ### Objections 1. **ID:** C1 | **Severity:** Blocking|Important|Nit - **Objection:** ... - **Impact:** ... - **Suggestion:** ... ### Non-issues considered - [category]: why not applicable ### Loop control - **Approval blocked:** yes | no - **Blocking open:** [IDs] - **Recommend:** human-approve-ready | author-revise | human-override-needed | deadlock-human-required ``` End with skill `spec-handoff`.
From sushilti80/specforge-engineering-team, MIT.
More from sushilti80/specforge-engineering-team
- 0.524score
ui-a11y
sushilti80
Accessibility checklist for interactive UI: labels, keyboard, focus, contrast, and ARIA for overlays.
SkillBFreshness: BClaude Code +9 - 0.524score
spec-advisory
sushilti80
Readonly advisory mode — architecture review, compare options, feasibility, "should we", "critical review", "worth it", "review only".
SkillBFreshness: BClaude Code +9 - 0.524score
ui-forms
sushilti80
Build working forms: schema validation, field errors, submit/pending/disabled states, and accessible labels.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-agent-audit
sushilti80
Readonly audit of agent definition files in agents/ for memory & self-learning patterns, debugging patterns, description alignment, and contradicting…
SkillBFreshness: BClaude Code +9 - 0.521score
spec-arch-author
sushilti80
Write ARCH specs and ADRs from user-APPROVED REQ files.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-guardian-drift
sushilti80
Readonly compare .specs/ to codebase and flag drift.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-handoff
sushilti80
Standard HANDOFF block and checkpoint files for spec-driven pipeline.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-agent-memory
sushilti80
Read and update project agent memory in .agents/memory/.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-recipes
sushilti80
Need-based workflow recipes for eng-orchestrator.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-release-metrics
sushilti80
Record release efficiency against need-based plans: planned vs run agents, estimated tokens (minimal mode), human gates, quality KPIs.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-req-author
sushilti80
Write or update REQ specs in .specs/requirements/.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-token-budget
sushilti80
Token and output budgets by task type.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 12, 2026 (3 months ago)
- Last release
- Aug 6, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sushilti80
- 0.524score
ui-a11y
sushilti80
Accessibility checklist for interactive UI: labels, keyboard, focus, contrast, and ARIA for overlays.
SkillBFreshness: BClaude Code +9 - 0.524score
ui-forms
sushilti80
Build working forms: schema validation, field errors, submit/pending/disabled states, and accessible labels.
SkillBFreshness: BClaude Code +9 - 0.524score
spec-advisory
sushilti80
Readonly advisory mode — architecture review, compare options, feasibility, "should we", "critical review", "worth it", "review only".
SkillBFreshness: BClaude Code +9 - 0.521score
spec-guardian-drift
sushilti80
Readonly compare .specs/ to codebase and flag drift.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-arch-author
sushilti80
Write ARCH specs and ADRs from user-APPROVED REQ files.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-agent-memory
sushilti80
Read and update project agent memory in .agents/memory/.
SkillBFreshness: BClaude Code +9
Cite this page
spec-challenger skill. Agent Mart. https://agentmart.dev/skills/sushilti80-spec-challenger (last updated 2026-10-24)