@lyndonkl/identify-kill-list
BNames what the substacker writer should stop doing — habits with no evidence of use, goals that became theatre, sections with 2 consecutive dormant quarters, and agents in the team whose output the writer ignores. Produces a bulleted list, each item with one sentence of why. Max 4 items. Ordered by ease (easiest first). Used once per Growth Strategist review. Trigger keywords: kill list, stop doing, what to cut, dead habits, dormant, ignored output.
Install
agr install @lyndonkl/identify-kill-list --target claudeWrites 1 file into .claude/skills/, pinned to git-ae6af9f7.
- .claude/skills/identify-kill-list/SKILL.md
Document
name: identify-kill-list description: Names what the substacker writer should stop doing — habits with no evidence of use, goals that became theatre, sections with 2 consecutive dormant quarters, and agents in the team whose output the writer ignores. Produces a bulleted list, each item with one sentence of why. Max 4 items. Ordered by ease (easiest first). Used once per Growth Strategist review. Trigger keywords: kill list, stop doing, what to cut, dead habits, dormant, ignored output.
Identify Kill List
Workflow
Per quarterly review:
- [ ] Step 1: Candidate sources:
- Sections classed "candidate-for-prune" in section-portfolio-assessment
- Goals unchanged 2 quarters in a row with no progression
- Agents in the team whose output the writer has not referenced in any decision this quarter
- Habits writer flagged in audience-notes as guilt-producing but unused
- [ ] Step 2: Filter to max 4 items (ruthless)
- [ ] Step 3: Order by ease: easiest kills first
- [ ] Step 4: Each item: one-sentence why
Rules
- Max 4 items. More than 4 and the writer won't stop any of them.
- First kill should be something the writer will actually do within a week.
- Last kill can be harder (a habit, a section) — but still named.
Worked example
- Drop the daily trend-scout digest. You haven't acted on any item from it in 12 weeks.
- Kill the "book reviews" section. One post in two quarters; it's guilt scaffolding, not a section.
- Stop writing the weekly "state of the publication" note to yourself. The Growth Analyst's report is doing that job now.
- Remove the "get on Hacker News front page" goal. It's not a goal, it's an outcome, and chasing it warps the writing.
Guardrails
- Never exceed 4 items.
- Order by ease. First item should be actionable this week.
- One-sentence rationale each. No paragraphs.
- Pull from multiple candidate sources — don't have all 4 be sections.
- Never suggest killing something the writer explicitly committed to this quarter.
- Previous-quarter kills that the writer didn't execute can be re-named — but only once, not indefinitely.
Trustgrade B
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- warnLicenseno SPDX license detected
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-ae6af9f7e3b62026-07-31