decision-log
Skill0 starsChanged 45 days agoMITView on GitHub
Appends one dated line to append-only DECISIONS.md using the real clock, zone by UTC offset (CST/CDT). Not the project record. Use when: "log this decision", "note that we decided X", "record the call we just made".
46 other projects use a version of this.
Adopted by
Most recently taken up by
- CharleneTStrain/product-ops-skillstheir own version, first seen Nov 8, 2026
- MichinaoShimizu/kirokutheir own version, first seen Nov 1, 2026
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- aya-taleb/productivity-skillstheir own version, first seen Nov 1, 2026
- warstellar/agent-skillstheir own version, first seen Oct 24, 2026
- rterakedis/leanwheel-skillstheir own version, first seen Oct 17, 2026
Used with
Projects with it also use product-brief, pre-mortem and 10 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.
erik-kroonSkillproduct-brief
Turn conversation context, codebase findings, and product intent into a PRD-style brief without assuming a specific issue tracker. Use when the user wants a PRD, product brief, feature spec, or implementation-ready product artifact.
Also in 3 projects that use this
Ingramradical235Skillpre-mortem
Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.
Also in 3 projects that use this
MicrosoftSkillretrospective
Review how work went and improve the next round. USE WHEN asked for a retro, delays, or process lessons. DO NOT USE for code review or transcript replay.
Also in 4 projects that use this
OpenAISkillmeeting-prep
Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.
Also in 3 projects that use this
Microsoft AzureSkilltest
Also in 3 projects that use this
HashiCorpSkillchangelog
Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.
Also in 3 projects that use this
Other versions46 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 46
- davekilleen/Dex★ 509same name
- zrosenfield/sharepoint-ai-skills★ 96same name
- GTMify/aigtm★ 25same name
- Sapere-IA/sdd-onboarding-kit★ 19same name
- ulises-jeremias/agent-toolkit★ 19same name
- Fadi88/one-man-startup★ 16same name
- Unabyss/unabyss-skills★ 15same name
- WupfAGI/claude-investment-skills★ 14same name
- lglucas/ai-dev-operating-system★ 12same name
- carlkibler/agent-skills★ 6same name
36 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- audit-codeSkill
- audit-docsSkill
- auditSkill
- bisect-driverSkill
- coding-conventionsSkill
- commit-gateSkill
- compact-ioSkill
- cron-task-manageSkill
- cve-auditSkill
- data-integrity-auditSkill
- deck-builderSkill
- determinism-guardSkill
- etl-validateSkill
- experiment-logSkill
- fetch-firstSkill
- flaky-test-detectorSkill
- github-repo-polishSkill
- golden-lockSkill
- history-leak-scanSkill
- landing-checkSkill
- llm-eval-harnessSkill
- local-secrets-manageSkill
- long-taskSkill
- milestone-trackSkill
- opus-workersSkill
- path-quirk-auditSkill
- reorg-proposalSkill
- research-briefSkill
- seed-controlSkill
- shell-portabilitySkill
- skill-vetSkill
- small-taskSkill
- token-squeezeSkill
- venue-fitSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 39 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
NOT the append-only project record or a handoff snapshot — those belong to a project-memory system (see the companion claude-project-memory …
- Very specific: line 99
Every .md file this skill creates or writes to gets ASCII characters only (bytes 0x00-0x7F) in the text you add.
- Very specific: line 107
Check before saving. In a git repo, git diff -U0 -- <file> | grep -v '^+++' | grep '^+' | grep -nP '[^\x00-\x7F]' must print nothing.
- Distinctive: line 111
Leave non-ASCII in text you did not write.
“Common” is measured: kept by at least 6 in 10 of the 39 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.
Files
decision-log — append a dated decision line
The engine is decision-log.js (portable Node, zero deps). It writes a single
timestamped line per decision to a plain DECISIONS.md. This is deliberately
NOT the append-only project record or a handoff snapshot — those belong to a
project-memory system (see the companion claude-project-memory repo). It is
the lightweight one-liner you jot when a call gets made; the line it prints to
stdout is formatted to paste straight into a record entry later.
The timestamp always comes from the machine's real clock at runtime (new
Date()) — never a caller-supplied date — and the zone is labelled from the
ZONES map at the top of the script. It ships defaulted to a DST-aware US
Central rule: UTC-6 → CST, UTC-5 → CDT, and any other offset prints as a
literal UTC±H:MM. The file is append-only: existing lines are never rewritten,
and a missing file is created with a one-line header.
Commands
node decision-log.js add "<decision>" [--why "<reason>"] [--file DECISIONS.md]
node decision-log.js list [--file DECISIONS.md]
node decision-log.js --canary- add stamps the current clock and appends the line, printing it to stdout.
Missing decision text exits 2.
--whyadds a(why: <reason>)clause.--filetargets a different log (default./DECISIONS.md). - list prints every entry line (the
-lines) in file order.
Examples
- Freeze call with a reason:
node decision-log.js add "keep the factor weights frozen" --why "frozen regression must stay byte-exact"→- 2026-07-21 10:37 CDT - decided: keep the factor weights frozen (why: frozen regression must stay byte-exact) - Log to another project's file:
node decision-log.js add "guardian consent is the hard launch gate" --file ../other-project/DECISIONS.md - Review what's been decided:
node decision-log.js list
Copy the printed line into a project-memory record entry when you next append the record — that is the intended handoff between the two.
Setting your timezone
Zone labelling is one clearly-commented const at the top of decision-log.js:
const ZONES = { 360: "CST", 300: "CDT" };The keys are getTimezoneOffset() minutes (minutes to ADD to local time to
reach UTC, so a zone BEHIND UTC is POSITIVE): UTC-6 → 360, UTC-5 → 300. It
defaults to US Central. Edit the map for your timezone — e.g. { 0: "UTC" },
or { 480: "PST", 420: "PDT" } for US Pacific. Any offset not listed falls
back to a literal UTC±H:MM label, so the tool still works unedited anywhere.
Windows notes
- PowerShell 5.1: quote the decision and reason as whole double-quoted
arguments:
add "adopt GitHub Flow" --why "cleaner PR history". PS 5.1 has no&&/||/ternary, but this is a single command so that does not bite. - Node writes the file as UTF-8 directly — do NOT pipe through
Set-Content(it defaults to the ANSI codepage and would mangle a—or non-ASCII text).
Storage
A single append-only DECISIONS.md (default in the cwd; override with --file).
One header line, then one - ... line per decision. Commit it if you want the
decisions in version history.
Exit codes
0 ok · 1 canary failure · 2 usage error (missing decision text / unknown command / unwritable or invalid --file path).
Verification (the done-check)
node decision-log.js --canarySelf-tests both directions in a throwaway temp file: a valid add writes a
well-formed line whose date equals the system date and whose zone label matches
the current UTC offset (recomputed independently in the canary from the same
ZONES map), --why appears only when given, a second add appends without
disturbing the first line, and missing decision text exits 2 without creating a
file. MUST print CANARY PASS n/n before you trust a result.
node decision-log.js --canary — MUST print CANARY PASS 29/29 before you trust a result.
ASCII-only markdown (rule added 2026-09-23)
Every .md file this skill creates or writes to gets ASCII characters only
(bytes 0x00-0x7F) in the text you add. No exceptions for headings, tables,
quotes, names or pasted tool output.
- Dashes:
-(never an en or em dash). Arrows:->and<-. Quotes: straight"and'. Ellipsis:.... Math:x,+/-,<=,>=,~. Separators:-,;or|. No emoji, no check-mark glyphs (use[x]and[ ]), no accented letters: transliterate names and quoted text. - Check before saving. In a git repo,
git diff -U0 -- <file> | grep -v '^+++' | grep '^+' | grep -nP '[^\x00-\x7F]'must print nothing. For a new or untracked file,grep -nP '[^\x00-\x7F]' <file>must print nothing. - Leave non-ASCII in text you did not write. Earlier entries of an append-only record stay byte for byte; converting an existing file is a separate, explicit job.
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
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.

