agentleFS
Yesterday-AIYesterday-AI/ytstack/skills/plan-eng-review/SKILL.md

plan-eng-review

Skill2 starsChanged 30 days agoMITView on GitHub

Reviews the execution approach of a pitch or a sliced milestone for feasibility, architecture, data flow, edge cases, test coverage, performance and security, through the installed gstack plan-eng-review skill. Use after plan-ceo-review on a pitch, or after slice-milestone and before plan-task on M###-S##-PLAN.md; also when the user says eng review, architecture review, lock the approach. Not for scope and ambition questions (plan-ceo-review).

51 other projects use a version of this, 7 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use qa-only, land-and-deploy and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ramybarsoumSkill

    qa-only

    Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps, but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes.

    Also in 17 projects that use this

  • ayudaySkill

    land-and-deploy

    Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production".

    Also in 14 projects that use this

  • seek888Skill

    plan-devex-review

    Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to "DX review", "developer experience audit", "devex review", or "API design review". Proactively suggest when the user has a plan for developer-facing products (APIs, CLIs, SDKs, libraries, platforms, docs). (gstack) Voice triggers (speech-to-text aliases): "dx review", "developer experience review", "devex review", "devex audit", "API design review", "onboarding review".

    Also in 11 projects that use this

  • ramybarsoumSkill

    design-consultation

    Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pages. Creates DESIGN.md as your project's design source of truth. For existing sites, use /plan-design-review to infer the system instead. Use when asked to "design system", "brand guidelines", or "create DESIGN.md". Proactively suggest when starting a new project's UI with no existing design system or DESIGN.md.

    Also in 18 projects that use this

  • ayudaySkill

    unfreeze

    Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits".

    Also in 14 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 6 projects that use this

  • +1 more from ramybarsoum
  • +3 more from ayuday

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Mode = abort: If neither slice-plans nor a pitch artifact exist, abort with: "Run ytstack:office-hours first (concept-mode review) or …

    line 80
  2. Very specific:

    After the installed gstack plan-eng-review skill completes:

    line 82
  3. Very specific:

    If MODE is abort: stop with the abort message from the invocation notes (this gate comes first because it needs no gstack).

    line 91
  4. Very specific:

    If GSTACK_AVAILABLE is no (or unknown): stop.

    line 92
  5. Very specific:

    If GSTACK_PIN_OK is no: continue, but say once that the installed gstack (GSTACK_VERSION) is older than the version ytstack was tested with.

    line 93
  6. Very specific:

    If BUN_OK is no: continue, but warn that gstack's helpers need bun >= 1.4.2 and may fail.

    line 94

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ytstack:plan-eng-review

Thin wrapper around the installed gstack plan-eng-review skill (~/.claude/skills/gstack/plan-eng-review, ytstack tested against v1.96.0.0). Detects the ytstack mode (milestone vs concept), checks the install, invokes the gstack skill through the Skill tool so its procedure runs natively, then applies the outcome to ytstack artifacts. gstack is the single source of truth for the procedure; upstream updates arrive with the install.

ytstack context (resolved at render time)

# ytstack resolver (M016): checkout = where this shell runs, via the shared lib.
_LIB="${CLAUDE_SKILL_DIR}/../../hooks/lib/git-ctx.sh"
if [ -f "$_LIB" ]; then
  . "$_LIB"; yt_git_ctx "$PWD"; yt_resolve_yt_dir >/dev/null
  _PROJECT_DIR="$YT_TOPLEVEL"; _YT_DIR="$YT_DIR"; _YT_SCOPE="$YT_SCOPE"; _IS_GIT="$YT_IS_GIT"; _PROJECT_KEY="$YT_REPO_KEY"
else
  # Host did not substitute CLAUDE_SKILL_DIR (e.g. Codex adapter): project scope only.
  _IS_GIT=$([ "$(git rev-parse --is-inside-work-tree 2>/dev/null)" = true ] && echo yes || echo no)
  _PROJECT_DIR=$(git rev-parse --show-toplevel 2>/dev/null || pwd -P)
  _YT_DIR=""; _YT_SCOPE=none; _PROJECT_KEY=""
  [ -d "$_PROJECT_DIR/.ytstack" ] && { _YT_DIR="$_PROJECT_DIR/.ytstack"; _YT_SCOPE=project; }
fi
cd "$_PROJECT_DIR" 2>/dev/null || true
_PROJECT_SLUG=$(basename "$_PROJECT_DIR")
_CURRENT_MILESTONE=none
if [ -n "$_YT_DIR" ] && [ -f "$_YT_DIR/STATE.md" ]; then
  _CURRENT_MILESTONE=$(sed -n 's/^current_milestone: *//p' "$_YT_DIR/STATE.md" | head -1)
fi
_SLICE_PLANS=""
if [ -n "$_CURRENT_MILESTONE" ] && [ "$_CURRENT_MILESTONE" != "none" ] && [ -d "$_YT_DIR" ]; then
  _SLICE_PLANS=$(ls "$_YT_DIR"/$_CURRENT_MILESTONE-S[0-9][0-9]-PLAN.md 2>/dev/null | tr '\n' ' ')
fi
_PITCH=""
if [ -f "./OFFICE-HOURS.md" ]; then
  _PITCH="./OFFICE-HOURS.md"
elif [ -n "$_YT_DIR" ]; then
  _PITCH=$(ls "$_YT_DIR"/OFFICE-HOURS-*.md 2>/dev/null | head -1)
fi
if [ -n "$_SLICE_PLANS" ]; then
  _MODE=milestone
elif [ -n "$_PITCH" ] && [ -f "$_PITCH" ]; then
  _MODE=concept
else
  _MODE=abort
fi
# gstack precheck (M017): installed dependency, not vendored
if command -v yt_gstack_ctx >/dev/null 2>&1; then
  yt_gstack_ctx >/dev/null
  echo "GSTACK_AVAILABLE: $YT_GSTACK_AVAILABLE"; echo "GSTACK_DIR: $YT_GSTACK_DIR"; echo "GSTACK_VERSION: ${YT_GSTACK_VERSION:-none}"
  echo "GSTACK_PIN_OK: $YT_GSTACK_PIN_OK (pin v$YT_GSTACK_PIN)"; echo "GSTACK_SKILL_OK: $(yt_gstack_skill_ok plan-eng-review)"
  echo "BUN_OK: $YT_BUN_OK (${YT_BUN_VERSION:-none})"; echo "GSTACK_INSTALL_CMD: $YT_GSTACK_INSTALL_CMD"
else
  echo "GSTACK_AVAILABLE: unknown (shared lib not loaded)"
fi
echo "HAS_YTSTACK: $([ -n "$_YT_DIR" ] && echo yes || echo no)"
echo "MODE: $_MODE"
echo "CURRENT_MILESTONE: $_CURRENT_MILESTONE"
echo "SLICE_PLANS: ${_SLICE_PLANS:-none}"
echo "PITCH: ${_PITCH:-none}"

ytstack invocation notes

Two modes, auto-detected above:

Mode = milestone (slice-plans exist). The "plan" being engineering-reviewed is the current milestone's slice-plans. Read those files when the gstack skill asks what to review. Architecture, data flow, edge cases, test coverage, performance.

Mode = concept (no slice-plans yet; pitch artifact produced by ytstack:office-hours exists). The "plan" being engineering-reviewed is the pitch at _PITCH. Focus the review on feasibility + architectural risk of the pitched approach BEFORE any infra is scaffolded: is the target tech stack viable, are there hidden integration complexities, are the perf/scale expectations realistic, are there obvious security / data-handling gaps. Output the feasibility verdict + top 3 risk items. Concept-mode eng review is OPTIONAL per the locked greenfield flow (DECISIONS 2026-04-24); office-hours + plan-ceo-review can proceed to init-project without it.

Mode = abort. If neither slice-plans nor a pitch artifact exist, abort with: "Run ytstack:office-hours first (concept-mode review) or ytstack:slice-milestone first (milestone-mode review). plan-eng-review reviews existing plan content; it does not produce it." Do NOT invoke the gstack skill.

After the installed gstack plan-eng-review skill completes:

  • Milestone mode: apply review outcomes by editing the affected slice-plans (add edge cases, adjust tests, tighten scope). Append any locked architectural decision to DECISIONS.md in append-only format.
  • Concept mode: append the feasibility verdict + risk-item list as an annotation block at the top of _PITCH. If "go", recommend ytstack:init-project. If "stop / rescope", recommend revisiting office-hours on the affected question.

HARD-GATE: gstack installed?

This wrapper runs the gstack plan-eng-review skill that is installed on this machine (GSTACK_DIR above; ytstack is tested against gstack v1.96.0.0, bun >= 1.4.2). gstack is not vendored any more (DECISIONS 2026-11-07 "Vendor strategy").

  • If MODE is abort: stop with the abort message from the invocation notes (this gate comes first because it needs no gstack).
  • If GSTACK_AVAILABLE is no (or unknown): stop. Tell the user that ytstack:plan-eng-review needs gstack and print the one-line install command from GSTACK_INSTALL_CMD. Do not improvise the engineering review from memory.
  • If GSTACK_PIN_OK is no: continue, but say once that the installed gstack (GSTACK_VERSION) is older than the version ytstack was tested with.
  • If BUN_OK is no: continue, but warn that gstack's helpers need bun >= 1.4.2 and may fail.

Procedure

  1. Invoke the Skill tool with plan-eng-review (the installed gstack skill, not ytstack:plan-eng-review). When it asks what to review, answer from MODE: milestone -> the files in SLICE_PLANS; concept -> PITCH. Follow it to completion.
  2. Apply the ytstack post-processing for the detected mode from "ytstack invocation notes" above.
  3. Report the outcome and the recommended next skill. Do NOT auto-invoke any downstream skill.

Checklist

You MUST create a TodoWrite task for each of these items:

  1. Run preamble -- resolver, mode detection, gstack precheck flags
  2. HARD-GATE -- abort without plan content; stop with the install command when gstack is missing
  3. Invoke installed plan-eng-review via the Skill tool, pointing it at the mode's plan files
  4. Post-process -- slice-plan edits + DECISIONS (milestone) or pitch annotation (concept)
  5. Report + return -- outcome + next step, no auto-chaining

Terminal State

Return control after reporting the feasibility verdict and the recommended next skill: milestone mode -> ytstack:plan-task (or ytstack:spawn-milestone-team); concept mode -> ytstack:init-project on "go", ytstack:office-hours on "stop / rescope". Abort paths (no plan content, no gstack) return with the message only. Do NOT auto-invoke any downstream skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.