SkillAgentSearch skills...

decision-journal

Decision journal (tradeoffs, lessons learned), deferred-capture contract ([Deferred] issues, CLI args, source labels), storage templates. Use to log a lesson.

Install / Use

npx skills add athola/claude-night-market --skill decision-journal

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Category

Automation

Supported Platforms

Universal

Tags

Our assessment of decision-journal

decision-journal scores 82/100 on our quality scale, 2303rd of 2,758 Automation skills we index.

Its SKILL.md is 6.6 KB long, well organised into 14 sections and no code examples: a thorough specification that gives an agent plenty to work with.

It has 338 GitHub stars, a meaningful sign that others use it.

Substance
29/30
Structure
13/20
Description
15/15
Adoption
11/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so decision-journal is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-11-22. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

decision-journal compared with similar skills

All 4 of these similar skills score higher than decision-journal; compare them before choosing.

SkillScoreStarsUpdatedFormat
decision-journal (this skill)by athola8233859d agoSKILL.md
Agent-Reachby Panniantong100114.0ktodayCLAUDE.md
rufloby ruvnet10082.3ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10040.6k12d agoCLAUDE.md
Scraplingby D4Vinci100104.9k5d agoMCP Server

Frequently asked questions

How do I install decision-journal?
Run npx skills add athola/claude-night-market --skill decision-journal. The install tabs above show the steps for each supported agent.
Which AI agents does decision-journal work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is decision-journal safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is decision-journal still maintained?
The repository was last updated about 2 months ago, so decision-journal is actively maintained.

name: decision-journal description: Decision journal (tradeoffs, lessons learned), deferred-capture contract ([Deferred] issues, CLI args, source labels), storage templates. Use to log a lesson. alwaysApply: false modules:

  • modules/deferred-capture.md
  • modules/storage-templates.md
  • modules/template-patterns.md
  • modules/lifecycle-stages.md
  • modules/storage-patterns.md

Decision Journal Contract

When To Use

  • A workflow has just made a decision and needs to record the tradeoff: what was chosen, what was rejected, what was sacrificed.
  • A workflow has hit a failed approach, rework, or blocker and needs to record the lesson.
  • Building or validating a consumer hook that writes to the journal.
  • Building or validating a plugin's deferred-capture wrapper, or adding a source label (load modules/deferred-capture.md).
  • Choosing a template, maturity stage, or file name for stored knowledge (load modules/storage-templates.md).

When NOT To Use

  • Scaffolding the files at project init (that is attune:project-init).
  • Recording a full architecture decision that warrants a numbered ADR in docs/adr/. Reference its number from a journal entry instead of duplicating it.

This is a convention and a helper rather than a hard runtime dependency. Consumers degrade gracefully when leyline is absent (see Fallback).

What This Captures, And Why

AI-assisted work tends to narrate tool output ("the agent built X") and lose the human reasoning: the decision, the road not taken, and the honest rework nobody mentions. Two append-only logs, co-located with the code, fix that:

  • docs/tradeoffs.md records decisions and the alternatives sacrificed.
  • docs/lessons-learned.md records insights, failed approaches, and rework, framed blamelessly.

Files And Discipline

Both files are in docs/ (co-location is the strongest anti-staleness lever). Each is a single append-only running log with a scannable ## Active index at the top and an ## Archive section at the bottom.

  1. Append-only. An accepted entry is never edited or deleted. Only its Status changes.
  2. Supersede, do not overwrite. A reversal adds a new entry, flips the old entry's status to superseded-by: <new-id>, and links both ways.
  3. Stable IDs (TR-001, LL-001) so links from PRs, commits, and code never break.
  4. Every entry links back to its PR, commit, or issue.

Status vocabularies:

  • Tradeoffs: proposed -> accepted -> (superseded-by: TR-NNN | deprecated)
  • Lessons: open -> actioned -> closed

Capture UX: Draft And Confirm

When a workflow reaches a decision or lesson point:

  1. Draft the entry from the live context of the phase (the options weighed, what was given up, the failure and its root cause).
  2. Show the draft to the human and let them confirm or edit.
  3. Append it. Tradeoffs start proposed, and lessons start open.

Do not auto-write without the confirm step. The point is to capture the human reasoning.

CLI Interface

Run the helper from leyline:

python3 ${LEYLINE}/scripts/journal_append.py <tradeoffs|lessons> \
  --project-root <repo-root> \
  --title "<short title>" \
  [--phase <phase>] [--status <status>] \
  [--field key=value ...] \
  [--json '<full field object>'] \
  [--supersedes TR-NNN] \
  [--dry-run]

The helper assigns the next ID, renders the template, inserts the entry above the ## Archive marker, updates the active index, and (with --supersedes) flips the prior entry's status and adds backlinks. It is idempotent: appending an entry whose substantive fields already appear is a no-op.

Tradeoff fields

title (required), context, drivers (list), options (list of {name, pros, cons, chosen}), decision, ystatement, consequences_positive, consequences_negative, phase, deciders, links. Prefer --json for the list-valued fields. status and date are auto-set (proposed / today) but can be overridden.

Lesson fields

title (required), what_happened, what_went_well, what_didnt_work, root_cause, action, category, owner, phase, links. status and date are auto-set (open / today) but can be overridden.

Fallback (leyline Absent)

The entry template ships inside each scaffolded file as an HTML-comment footer (<!-- ENTRY TEMPLATE ... -->). When the helper is unavailable, a consumer (or a human) copies that block into the section above ## Archive, assigns the next sequential ID, fills it in, and adds an index row by hand. The fallback template covers the same core sections as the canonical one so entries stay consistent across the two paths.

Consumer Hook Shape

Each workflow adds one block at its natural endpoint:

Record to the decision journal (draft + confirm):
- If leyline is installed: run journal_append.py for a {tradeoff|lesson},
  drafting fields from this phase's context; show the draft; append on
  confirm.
- Fallback (leyline absent): append to docs/{tradeoffs|lessons-learned}.md
  using the footer ENTRY TEMPLATE; assign the next sequential ID.

Compliance Test

python3 ${LEYLINE}/scripts/journal_append.py tradeoffs \
  --title "Compliance check" --field context="verify" --dry-run

Must print a rendered entry containing ## TR-001: and write nothing.

Related Contracts

  • modules/deferred-capture.md: the CLI, issue template, label taxonomy, duplicate detection, and JSON output that every plugin deferred-capture wrapper implements. Load it when building or checking a wrapper.
  • modules/storage-templates.md: seedling, growing, evergreen, and reference templates, the promotion lifecycle, and naming conventions. Load it when organizing a knowledge store. Detail is in template-patterns, lifecycle-stages, and storage-patterns.

Exit Criteria

  • [ ] docs/tradeoffs.md and docs/lessons-learned.md exist with a ## Active index and an ## Archive section.
  • [ ] A new entry has a unique TR-NNN/LL-NNN id and an index row.
  • [ ] Superseding an entry flips the old status to superseded-by: <id> and adds bidirectional links. The old entry is not deleted.
  • [ ] Re-running the same append is a no-op (idempotency holds).
  • [ ] A consumer with leyline absent still produces a correctly shaped entry from the in-file ENTRY TEMPLATE.

The last criterion holds even for consumers that name leyline in their dependencies. That field is marketplace metadata; no installer acts on it, so spec-kit or imbue can be installed without leyline present. The fallback guards that boundary. Do not remove it as leftover code. See docs/metadata.md, "What dependencies Does Not Mean".

Related Skills

View on GitHub
GitHub Stars338
CategoryAutomation
Updated1mo ago
Forks35

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions