New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Flow Next Spec Completion Review

by gmickel in gmickel/flow-next

Spec completion review - verifies all spec tasks implement the spec requirements.

MITAuto-check passedDevelopment

Install Flow Next Spec Completion Review

skills CLI
$ npx skills add gmickel/flow-next --skill flow-next-spec-completion-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gmickel/flow-next flow-next-spec-completion-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gmickel/flow-next.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/flow-next/skills/flow-next-spec-completion-review .claude/skills/flow-next-spec-completion-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
flow-next-spec-completion-review
GitHub stars
709
Token cost
~2.1k tokens
SKILL.md length
915 words
Files
10 (incl. references)
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

Spec completion review - verifies all spec tasks implement the spec requirements.

  • Works in 5 steps: Parse Arguments → 5: Resume terminal status persistence… → Load Backend Workflow → …
  • /flow-next:spec-completion-review
  • SKILL.md covers Preamble — execute Phase 0…, Backend Selection, Critical Rules and Input, plus 1 more section
  • Calls jq, git and cursor

What it does

Flow Next Spec Completion Review is an agent skill from gmickel/flow-next. Spec completion review - verifies all spec tasks implement the spec requirements. Triggers on /flow-next:spec-completion-review.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `references/backend-at-a-glance.md`, `references/completion-review-prompt.md` and `references/terminal-status.md`).

It sits in Development. The repository describes itself as: Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in… The licence is MIT.

When your agent uses it

  • /flow-next:spec-completion-review

Example prompts

  • “/flow-next-spec-completion-review”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Parse Arguments
  2. 5: Resume terminal status persistence before dispatch
  3. Load Backend Workflow
  4. Execute the backend workflow
  5. Fix loop and terminal status

What it can do on your machine

Read from SKILL.md and the folder at commit c1ce203. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • git
    • cursor
    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Flow Next Spec Completion Review loads about 2.1k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 915 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gmickel/flow-next at commit c1ce203, republished under its MIT licence (© gmickel). 915 words, ~2,120 tokens.

Download SKILL.mdSave it as .claude/skills/flow-next-spec-completion-review/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
flow-next-spec-completion-review
description
Spec completion review - verifies all spec tasks implement the spec requirements. Triggers on /flow-next:spec-completion-review.
user-invocable
false

Spec Completion Review Mode

Workflow is backend-split. Read workflow-common.md for Phase 0 (backend detection + philosophy), then read ONLY the file matching your active backend:

Do not load the others — only the active backend's file is needed.

Verify that the combined implementation of all tasks in a spec satisfies the spec requirements. This is NOT a code quality review (that's impl-review's job) — this confirms spec compliance only.

Role: Spec Completion Review Coordinator (NOT the reviewer) Backends: Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), Claude Code CLI (claude), or host-native (host)

Read working-rules.md first unless you already have this run; it holds for every step of this skill.

Preamble — execute Phase 0 exactly once

The executable Phase 0 lives in workflow-common.md §"Phase 0: Backend Detection" — Read it and execute it ONCE, before any other bash in this skill. It defines $FLOWCTL (bundled — NOT installed globally; which flowctl fails, expected), resolves $BACKEND via the single flowctl review-backend call, and handles the ASK / none cases. Never invoke flowctl review-backend a second time in the same run.

Exception: a --review=<backend> argument (see Backend Selection below) wins — when present, set BACKEND from the flag and skip Phase 0's review-backend call + ASK handling (still run its $FLOWCTL setup lines). An explicit --review=rp or --review=export was removed: tell the user in one line "RepoPrompt review (rp, export) was removed in flow-next 8.0.0; review backends: claude, codex, copilot, cursor, host." and stop as for ASK.

Backend Selection

Priority (first match wins):

  1. --review=<backend> or --review <backend> argument (codex|copilot|cursor|claude|host|none)
  2. FLOW_REVIEW_BACKEND env var — bare backend (codex, copilot, cursor, claude, host, none) OR spec form (codex:<model>:xhigh, copilot:<model>, cursor:<model>, claude:<model>:<effort>); host is bare-only (host:<model> is rejected)
  3. .flow/config.json → review.backend (same bare / spec forms)
  4. Error - no auto-detection
Backend at a glance

The per-backend summary (models, env vars, --spec forms and FLOW_REVIEW_BACKEND spec-form examples) and the backend[:model[:effort]] spec grammar live in references/backend-at-a-glance.md. Read it only when you surface backend guidance to the user (ASK branch, recommendation, override hint) — routing does not need it.

Critical Rules

Per-backend critical rules live in the backend file you route to (workflow-codex.md, workflow-copilot.md, workflow-cursor.md, workflow-claude.md) — each opens with its own Critical rules section. The host safety invariant and the all-backends rules stay here because they gate routing itself.

For host backend: host is bare-only. After selection, read workflow-host.md. The review must use a fresh, tool-enforced read-only reviewer from a different model family and fail closed when no cross-family pin is available.

For all backends:

  • If REVIEW_RECEIPT_PATH set: write receipt after SHIP verdict (codex writes automatically via --receipt)
  • Any failure → output RETRY: no verdict (backend or transport failure) and stop; when its CLI message: reports a usage, credit or spend limit, report that message instead of RETRY:, since a retry fails the same way. No-verdict transport failures are recorded and their reserved round refunded; never manually reset the review counter. Exit 5 / TRANSPORT_UNHEALTHY stops automatic retries until the backend is repaired.

The three hard invariants (never self-declare SHIP, never mix backends, never skip review silently) live with the shared anti-patterns in workflow-common.md §"Anti-patterns (all backends)".

Input

Arguments: $ARGUMENTS Format: <spec-id> [--review=codex|copilot|cursor|claude|host|none]

  • Spec ID - Required, e.g. fn-1 or fn-22-53k
  • --review - Optional backend override

Workflow

bash
REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
Step 0: Parse Arguments

Parse $ARGUMENTS for:

  • First positional arg matching fn-* → SPEC_ID
  • --review=<backend> → backend override
  • Remaining args → focus areas
Show full SKILL.md (358 more words)Show less
Step 0.5: Resume terminal status persistence before dispatch

Run this checkpoint after parsing SPEC_ID and before loading or dispatching any backend. Run the same checkpoint again immediately after host records a verdict. It recovers a terminal status write that failed after the verdict round was durably consumed, without reserving or dispatching another review. Host terminal status has one owner, review-rounds record --status-target completion (with a journaled receipt, that status leg lands when the receipt publishes); this checkpoint only repairs a write that did not land. A stored not_required (work's 3g policy skip) is neither ship nor unknown here: the checkpoint has no terminal attempt to resume for it, and an explicit manual invocation may still run a real review and overwrite it with ship/needs_work — the upgrade direction is legal, while the skip's own write stays gated on unknown.

bash
TERMINAL_REVIEW_JSON="$($FLOWCTL review-rounds resume-terminal "$SPEC_ID" --review-type completion --json)" || exit $?
TERMINAL_ACTION="$(printf '%s' "$TERMINAL_REVIEW_JSON" | jq -r '.action')"
TERMINAL_STATUS="$(printf '%s' "$TERMINAL_REVIEW_JSON" | jq -r '.status')"
TERMINAL_EXIT="$(printf '%s' "$TERMINAL_REVIEW_JSON" | jq -r '.exit')"
case "$TERMINAL_ACTION" in
  continue) ;;
  retry) echo "RETRY: no verdict (backend or transport failure)"; exit "$TERMINAL_EXIT" ;;
  ship) echo "VERDICT=SHIP"; exit "$TERMINAL_EXIT" ;;
  superseded) echo "COMPLETION_REVIEW_STATUS=$TERMINAL_STATUS"; exit "$TERMINAL_EXIT" ;;
  escalate)
    if [ "$TERMINAL_STATUS" = needs_human ]; then
      echo "ESCALATE: reviewer requested human review"
    else
      echo "ESCALATE: completion-review did not converge within the verdict-round cap"
    fi
    exit "$TERMINAL_EXIT" ;;
  *) echo "Unknown terminal review action: $TERMINAL_ACTION" >&2; exit 1 ;;
esac

An exit-4 cap refusal before this run has delivered a completion verdict is non-terminal for completion status: surface ESCALATE: / NEEDS_HUMAN and do not invent a needs_work write. More than ${MAX_REVIEW_TRANSPORT_FAILURES:-2} consecutive transport failures stop separately with TRANSPORT_UNHEALTHY + exit 5; never write completion status or reset the verdict counter for transport health.

Unchanged-artifact terminal: NOT_RETRYABLE: artifact unchanged since last verdict exits 1 before dispatch. Stop for human action; never refund, reset, use --force, or redispatch autonomously. A human may edit the exact artifact, explicitly reset, or deliberately apply --force.

Step 1: Load Backend Workflow
  1. $BACKEND was already resolved by workflow-common.md Phase 0 (Preamble) — do NOT re-run it.
  2. Read only the file for that backend, per the routing table at the top of this file.

Do not read the other backend files. Each is self-contained for its backend; loading the others wastes context.

Step 2: Execute the backend workflow

Follow the phases in the per-backend file end-to-end. Each file owns its own Identify → Execute → Verdict → Receipt steps.

Step 3: Fix loop and terminal status

Both are backend-agnostic and live in workflow-common.md — already in context from Phase 0:

  • §"Fix Loop (INTERNAL)" — the round cap, the anti-patterns, and the parse → fix → commit → re-review cycle.
  • §"Record the terminal verdict exactly once" — who writes completion_review_status, and when host re-runs the Step 0.5 checkpoint above.

© gmickel, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in plugins/flow-next/skills/flow-next-spec-completion-review of gmickel/flow-next.

  • SKILL.md
  • references/backend-at-a-glance.md
  • references/completion-review-prompt.md
  • references/terminal-status.md
  • workflow-claude.md
  • workflow-codex.md
  • workflow-common.md
  • workflow-copilot.md
  • workflow-cursor.md
  • workflow-host.md

Open the folder on GitHubat commit c1ce203

Compare with similar skills

Flow Next Spec Completion Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Flow Next Spec Completion Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flow Next Spec Completion Review this skillgmickel/flow-next709—~2.1kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from gmickel/flow-next

All 43 skills in this repo

  • Flow Next Resolve PR

    gmickel/flow-next

    Resolve PR review feedback. An agent skill from gmickel/flow-next.

    709 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Flow Next Resolve PR

    gmickel/flow-next

    Resolve PR review feedback — fetch unresolved threads, triage, dispatch per-thread resolver agents, validate, commit, reply + resolve via GraphQL.

    709 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Flow Next

    gmickel/flow-next

    Manage .flow/ tasks and specs. An agent skill from gmickel/flow-next.

    709 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Flow Next Audit

    gmickel/flow-next

    Audit .flow/memory/ entries against the current codebase and decide Keep / Update / Consolidate / Replace / Delete / Harden per entry.

    709 GitHub stars~3.1k tokensUpdated today
    Auto-check: notes

  • Flow Next Capture

    gmickel/flow-next

    Save the current conversation as a source-tagged flow-next spec, then offer review or editing.

    709 GitHub stars~1.9k tokensUpdated today
    Auto-check: notes

  • Flow Next Chart

    gmickel/flow-next

    Decision-map discovery for one oversized unclear idea before capture.

    709 GitHub stars~2.7k tokensUpdated today
    Auto-check: notes

Categories

Questions about Flow Next Spec Completion Review

What does Flow Next Spec Completion Review do?

Spec completion review - verifies all spec tasks implement the spec requirements. Flow Next Spec Completion Review is an agent skill from gmickel/flow-next. Spec completion review - verifies all spec tasks implement the spec requirements.

When should I use Flow Next Spec Completion Review?

Flow Next Spec Completion Review fits situations like: /flow-next:spec-completion-review.

How do I install Flow Next Spec Completion Review in Claude Code?

Run `npx skills add gmickel/flow-next --skill flow-next-spec-completion-review -a claude-code`. Or copy the skill folder (plugins/flow-next/skills/flow-next-spec-completion-review in gmickel/flow-next) into .claude/skills/flow-next-spec-completion-review in your project. Claude Code loads it when a task matches its description.

How do I install Flow Next Spec Completion Review in Codex?

Run `npx skills add gmickel/flow-next --skill flow-next-spec-completion-review -a codex`. Or copy the skill folder (plugins/flow-next/skills/flow-next-spec-completion-review in gmickel/flow-next) into .agents/skills/flow-next-spec-completion-review in your project. Codex loads it when a task matches its description.

Can I use Flow Next Spec Completion Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gmickel/flow-next --skill flow-next-spec-completion-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flow-next-spec-completion-review, .gemini/skills/flow-next-spec-completion-review, .github/skills/flow-next-spec-completion-review and .opencode/skills/flow-next-spec-completion-review in your project.

What does Flow Next Spec Completion Review need to run?

Going by SKILL.md and its folder, Flow Next Spec Completion Review needs the command-line tools its instructions call (jq, git, cursor and claude).

Does Flow Next Spec Completion Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Flow Next Spec Completion Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Flow Next Spec Completion Review use?

Flow Next Spec Completion Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flow Next Spec Completion Review use?

About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.

What are the alternatives to Flow Next Spec Completion Review?

Skills that share tags, products or a category with Flow Next Spec Completion Review: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flow Next Spec Completion Review?

gmickel (a GitHub user) maintains it in gmickel/flow-next, which has 709 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 10, 2026.

Source: gmickel/flow-next on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.