reflect
Mine this session's transcript for durable lessons with three parallel reviewers, then route each into a concrete skill edit, a backlog item, or a rejection.
Skill by brandondkong
Chalk Labs
Need help deploying reflect?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/brandondkong-reflect
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
Use cases: writing, productivity
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/reflect
What's inside
- Skill name
reflect- Description
- Mine this session's transcript for durable lessons with three parallel reviewers, then route each into a concrete skill edit, a backlog item, or a rejection. Use for /reflect, or after a task that took longer than it should have.
- License
- NOASSERTION
- Instructions
- 50 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- divergent-reviewer.md · references/
- judgment-reviewer.md · references/
- synthesizer.md · references/
- tooling-reviewer.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from brandondkong/bstack
- 0.521score
show-me-your-work
brandondkong
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result), audited against the…
SkillBFreshness: BClaude Code +9 - 0.521score
create-verification-skill
brandondkong
Generate a project-local verification skill (.claude/skills/verify-<app>) that launches the app, drives it like a user across CLI, daemon, service, or GUI…
SkillBFreshness: BClaude Code +9 - 0.521score
maintain-verification-skill
brandondkong
Audit a project's verify-<app> skill and feature map against source and a live run, then ship one PR of proven corrections or report clean or blocked.
SkillBFreshness: BClaude Code +9 - 0.521score
architect
brandondkong
Architect or design this.
SkillBFreshness: BClaude Code +9 - 0.521score
interrogate
brandondkong
Interrogate, adversarial review, challenge this, tear this apart.
SkillBFreshness: BClaude Code +9 - 0.521score
bstack-mode
brandondkong
Brandon's rigorous working mode.
SkillBFreshness: BClaude Code +9 - 0.519score
tdd
brandondkong
TDD, failing test first, regression test.
SkillBFreshness: BClaude Code +9 - 0.516score
technical-writing
brandondkong
Write or review docs, RFCs, readmes, PR descriptions, and commit messages to a layered standard.
SkillBFreshness: BClaude Code +9 - 0.516score
no-comments
brandondkong
Deep comment pass.
SkillBFreshness: BClaude Code +9 - 0.516score
arena
brandondkong
Arena this.
SkillBFreshness: BClaude Code +9 - 0.516score
blast-radius
brandondkong
Use for "what could this break", "blast radius of X", or a diff you don't trust.
SkillBFreshness: BClaude Code +9 - 0.516score
cpp-discipline
brandondkong
C++ rules for ownership, lifetime, const-correctness, error handling, and header hygiene.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 17, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- NOASSERTION
- Repository
- github.com/brandondkong/bstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from brandondkong
- 0.521score
create-verification-skill
brandondkong
Generate a project-local verification skill (.claude/skills/verify-<app>) that launches the app, drives it like a user across CLI, daemon, service, or GUI…
SkillBFreshness: BClaude Code +9 - 0.521score
interrogate
brandondkong
Interrogate, adversarial review, challenge this, tear this apart.
SkillBFreshness: BClaude Code +9 - 0.521score
maintain-verification-skill
brandondkong
Audit a project's verify-<app> skill and feature map against source and a live run, then ship one PR of proven corrections or report clean or blocked.
SkillBFreshness: BClaude Code +9 - 0.521score
bstack-mode
brandondkong
Brandon's rigorous working mode.
SkillBFreshness: BClaude Code +9 - 0.521score
architect
brandondkong
Architect or design this.
SkillBFreshness: BClaude Code +9 - 0.521score
show-me-your-work
brandondkong
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result), audited against the…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get reflect running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
reflect skill. Agent Mart. https://agentmart.dev/skills/brandondkong-reflect (last updated 2026-10-24)