decision-log
Append-only TSV decision trail (log.sh) for long, multi-phase or unattended work, ending in an audit with an Attention section.
Skill by duy-tung
Chalk Labs
Need help deploying decision-log?
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/duy-tung-decision-log
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: security
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
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/decision-log
What's inside
- Skill name
decision-log- Description
- Append-only TSV decision trail (log.sh) for long, multi-phase or unattended work, ending in an audit with an Attention section. Use when a run's forks must be trusted later.
- License
- NOASSERTION
- Instructions
- 105 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- body: contains an absolute path from the author's machine
Files (3)
- SKILL.md
- log.sh · scripts/
- template.tsv
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from duy-tung/tstack
- 0.565score
diagnose
duy-tung
Diagnose and fix bugs and perf regressions from a feedback loop that goes red first.
SkillAFreshness: AClaude Code +9 - 0.559score
principles
duy-tung
Fourteen named engineering principles as steering vocabulary.
SkillAFreshness: AClaude Code +9 - 0.559score
domain-modeling
duy-tung
Keep the project's domain language sharp: the CONTEXT.md glossary and ADRs, updated inline as terms settle.
SkillAFreshness: AClaude Code +9 - 0.559score
codebase-design
duy-tung
Deep-module vocabulary and design-before-code (caller usage first, design it twice).
SkillAFreshness: AClaude Code +9 - 0.559score
mobile
duy-tung
Swift, Kotlin and Dart type discipline and review checks: exhaustive sum types, decoding at the boundary, main thread and lifecycle, device proof.
SkillAFreshness: AClaude Code +9 - 0.559score
prototype
duy-tung
Throwaway code that answers one design question: a logic model, UI variants, or a script that settles an empirical fork.
SkillAFreshness: AClaude Code +9 - 0.558score
context-audit
duy-tung
Measure always-on context (settings, MCP, skills, CLAUDE.md, AGENTS.md, memory) and prune it with approval.
SkillAFreshness: AClaude Code +9 - 0.556score
prove
duy-tung
Prove a change on the real artifact, not a proxy, and return VERIFIED, NOT VERIFIED or INCONCLUSIVE with evidence.
SkillAFreshness: AClaude Code +9 - 0.556score
how
duy-tung
Explain how code works or where something should live, tracing real code with file and symbol citations.
SkillAFreshness: AClaude Code +9 - 0.556score
interrogate
duy-tung
Review a diff with parallel fresh reviewers per axis (standards, spec, adversarial), then judge findings into Act on, Consider, Noted, Dismissed.
SkillAFreshness: AClaude Code +9 - 0.556score
afk
duy-tung
Run work unattended under a written contract: fresh worker per unit, independent verifier, review, decision log, morning report.
SkillAFreshness: AClaude Code +9 - 0.556score
grilling
duy-tung
Interview the user in rounds until you share one understanding of a plan, with a recommended answer per question.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 29, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- NOASSERTION
- Repository
- github.com/duy-tung/tstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from duy-tung
- 0.565score
diagnose
duy-tung
Diagnose and fix bugs and perf regressions from a feedback loop that goes red first.
SkillAFreshness: AClaude Code +9 - 0.559score
codebase-design
duy-tung
Deep-module vocabulary and design-before-code (caller usage first, design it twice).
SkillAFreshness: AClaude Code +9 - 0.559score
domain-modeling
duy-tung
Keep the project's domain language sharp: the CONTEXT.md glossary and ADRs, updated inline as terms settle.
SkillAFreshness: AClaude Code +9 - 0.559score
mobile
duy-tung
Swift, Kotlin and Dart type discipline and review checks: exhaustive sum types, decoding at the boundary, main thread and lifecycle, device proof.
SkillAFreshness: AClaude Code +9 - 0.559score
principles
duy-tung
Fourteen named engineering principles as steering vocabulary.
SkillAFreshness: AClaude Code +9 - 0.559score
prototype
duy-tung
Throwaway code that answers one design question: a logic model, UI variants, or a script that settles an empirical fork.
SkillAFreshness: AClaude 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 decision-log 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
decision-log skill. Agent Mart. https://agentmart.dev/skills/duy-tung-decision-log (last updated 2026-10-24)