reflect SKILL.md skillA

reflect from byerlikaya/claude-starter-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add byerlikaya/claude-starter-kit/reflect@git:20260929.b7001cd

Pins git:20260929.b7001cd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
byerlikaya/claude-starter-kit
Path
plugin/skills/reflect/SKILL.md
Versions recorded
5
Latest version
git:20260929.b7001cd, committed Sep 29, 2026
First version recorded
Jul 12, 2026
Size
3,974 bytes
Repository stars
26
License
MIT

Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach — findings, not code. The step-back counterpart to iterate's refine-to-done loop.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Reflect — step back and audit the work, not just the code

<!-- routing-eval reads the next line; why it sits in the body: AGENT_TEMPLATE.md -->
Trigger phrases: "reflect", "retro", "retrospective", "what did we miss", "step back", "introspect"

## When
A nontrivial chunk of work just finished (a feature, a plan, a debugging session) and it's worth a deliberate
step back **before** committing or moving on. This is the meta-cognitive counterpart to [[iterate]]: iterate
drives a change *to* its exit test; reflect asks whether the exit test — and the approach behind it — was even
the right one. Skip it for a one-line, unambiguous change; there's nothing to reflect on.

## Measure first, then remember
Run **`bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-stats.sh"`** (Bash tool, not PowerShell) before answering anything below, and open the pass with what it
reports. A retro built only on recall is an interview with the least reliable witness in the room: the model
reconstructs a tidy story from a context that has already been summarised, and the stretches where it span on a
failing approach are exactly the ones it remembers least. The script counts what actually happened — prompts,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add byerlikaya/claude-starter-kit/reflect@sha256:7229ce794ef99e86

The line at the top of this page pins the label git:20260929.b7001cd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4mnjybqmjq7mp53k.svg)](https://markdownregistry.com/a/art_4mnjybqmjq7mp53k)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 12, 2026 and Sep 29, 2026, about one every 20 days.

versioncommittedcommitsizeaudit
git:20260929.b7001cd latest2026-09-29 b7001cd 3,974 BA view · diff
git:20260924.a4578232026-09-24 a457823 3,973 BA view · diff
git:20260730.b9a07402026-07-30 b9a0740 4,167 BA view · diff
git:20260728.e582c262026-07-28 e582c26 3,888 BA view · diff
git:20260712.2b290472026-07-12 2b29047 2,736 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3974 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

byerlikaya/claude-starter-kit · 26 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4mnjybqmjq7mp53k
GET https://markdownregistry.com/api/v1/resolve?ref=byerlikaya/claude-starter-kit/reflect
GET https://markdownregistry.com/api/v1/blob/7229ce794ef99e8681ea92cc2871098d9ca155d43aa69e371c757e6a6b5ea2b7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from byerlikaya/claude-starter-kit

CLAUDE.md@kit CLAUDE.md file
byerlikaya/claude-starter-kit · kit/CLAUDE.md
git:20261023.d169a6d · audit C · 26 stars
a11y SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/a11y/SKILL.md · Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen…
git:20261002.8bbdc23 · audit A · 26 stars
adr SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/adr/SKILL.md · Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under…
git:20260924.a457823 · audit A · 26 stars
api-design SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/api-design/SKILL.md · API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A…
git:20260924.a457823 · audit A · 26 stars
automode-policy SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/automode-policy/SKILL.md · Auto-mode classifier config: inspect what the classifier that answers permission prompts is configured with, and catch…
git:20260929.b7001cd · audit A · 26 stars
backend-architecture SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/backend-architecture/SKILL.md · Decide, record and apply the backend stack and architecture pattern. Use when backend work starts with no recorded…
git:20260926.aaa5dbc · audit A · 26 stars
brainstorm SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/brainstorm/SKILL.md · Divergent discovery BEFORE planning: turn a fuzzy ask into 2–4 scoped options + named unknowns, pick a direction, hand…
git:20260924.a457823 · audit A · 26 stars
ci-pipeline SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/ci-pipeline/SKILL.md · CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.
git:20260924.a457823 · audit A · 26 stars
commit-message SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/commit-message/SKILL.md · Conventional Commits: reads the staged diff and proposes `type(scope): summary`, with body/footer when needed. One…
git:20261028.f23020a · audit A · 26 stars
confidence-check SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/confidence-check/SKILL.md · Readiness gate BEFORE writing implementation code: does this already exist, does it fit the project's architecture, is…
git:20260925.68939f0 · audit A · 26 stars
crew-allow-verify SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/crew-allow-verify/SKILL.md · Allow a verify command the hook was refused for want of a rule, or list the ones refused.
git:20261028.7bca680 · audit A · 26 stars
crew-approve SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/crew-approve/SKILL.md · Approve the commit or push Claude just showed you (auto and dontAsk modes).
git:20261014.50f278d · audit A · 26 stars

Every file in byerlikaya/claude-starter-kit

Other files named reflect

reflect SKILL.md skill
cursor/plugins · pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
git:20261023.7054003 · audit A · 15,586 stars
reflect SKILL.md skill
cursor/plugins · harness/pstack/claude-code/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
git:20261023.7054003 · audit A · 15,586 stars
reflect SKILL.md skill
nightly-labs/openbot · marketplace/production-catalog/bundles/pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
git:20261013.9e6954c · audit A · 6,292 stars
reflect SKILL.md skill
michael-denyer/pstack-claude · plugins/pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
git:20261104.e66f85f · audit A · 4,103 stars
reflect SKILL.md skill
backnotprop/pstack · skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
git:20261024.18b6c36 · audit A · 3,692 stars
reflect SKILL.md skill
bradygaster/squad · packages/squad-cli/templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
v1.0.0-squad · audit A · 3,337 stars
reflect SKILL.md skill
bradygaster/squad · packages/squad-sdk/templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
v1.0.0-squad · audit A · 3,337 stars
reflect SKILL.md skill
bradygaster/squad · .squad-templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
v1.0.0-squad · audit A · 3,337 stars

Browse by kind, by grade A, or by owner.