speckit-review
Reviews implementation changes against requirements and updates task tracking for the spec-kit project.
Install
mkdir -p .claude/skills/speckit-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12118" && unzip -o skill.zip -d .claude/skills/speckit-review && rm skill.zipInstalls to .claude/skills/speckit-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review completed implementation work and update task status.Key capabilities
- →Load feature paths and specification files
- →Review implementation against `spec.md` and `plan.md`
- →Check code quality and test coverage
- →Run project test suites
- →Determine review outcome (Approved, Approved with Notes, Needs Changes)
- →Update task status in `tasks.md` for approved work
How it works
The skill loads project context, identifies the review target, conducts a thorough code review against specifications, runs tests, determines an outcome, and generates a detailed report.
Inputs & outputs
When to use speckit-review
- →Review code for a specific task ID
- →Validate implementation against spec.md
- →Update status of pending tasks
- →Check recent git changes against requirements
About speckit-review
Analyzes feature implementation progress against defined specifications and plans, verifies git diffs, and updates task lists.
Review completed implementation work and update task status.
When not to use it
- →When the project structure does not include a `.specify/` directory
- →For reviewing work not related to a specific task ID or recent changes
- →When a complete review report is not required
Limitations
- →Requires `spec-kit` project structure with `.specify/` directory
- →Relies on `tasks.md` for task status updates
- →Does not mark tasks as done for 'Needs Changes' outcome
How it compares
This skill provides a structured, multi-step code review process integrated with project specifications and task tracking, unlike a simple code diff review.
Compared to similar skills
speckit-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| speckit-review (this skill) | 0 | 5mo | Review | Intermediate |
| proof-of-work | 1 | 8mo | No flags | Intermediate |
| verification-before-completion | 0 | 4mo | Review | Intermediate |
| cmd-check | 0 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by pradeepmouli
View all by pradeepmouli →You might also like
proof-of-work
MadAppGang
Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring.
verification-before-completion
jnPiyush
Block false completion claims. Force the agent to identify the claim, run the exact verification command, read the actual output, compare against the claim, and only then report. Use whenever an agent is about to say "done", "fixed", "tests pass", "deployed", "loop complete", or close an issue.
cmd-check
pbulsink
GitHub Copilot Chat Assistant
skill-comply
klu-dev
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
gsd-validate-phase
lza6
Retroactively audit and fill Nyquist validation gaps for a completed phase
manage-skills
junnv93
Analyzes session changes to detect missing verification skills. Dynamically discovers existing skills, creates new skills or updates existing ones, and manages CLAUDE.md skill references. Use when adding new patterns/modules that may need verification coverage, or when maintaining skill consistency.