lyndonkl/skills/answer-uncomfortable-question
skills/answer-uncomfortable-question/SKILL.md
--- name: answer-uncomfortable-question description: Takes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad. --- # Answer Uncomfortable Question ## Workflow ``` Per question: - [ ] Ste
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/answer-uncomfortable-questionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 10:07 AM128.1s1 file scanned
SKILL.md
- name:
- answer-uncomfortable-question
- description:
- Takes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
Answer Uncomfortable Question
Workflow
Per question:
- [ ] Step 1: Reject if not answerable with current inputs → "I'd like to ask X, but I don't have the data. Here's what to collect before next quarter."
- [ ] Step 2: Gather evidence: numbers, quotes, specific posts. Cite them.
- [ ] Step 3: Write reasoning as a chain: evidence A → inference B → inference C → recommendation
- [ ] Step 4: Write downside: what SPECIFICALLY goes wrong if the recommendation is wrong?
- [ ] Step 5: End with one-line recommendation: do X / don't do X / watch Y
- [ ] Step 6: 200-400 words per question
Uncomfortable-question selection criteria
The Strategist chooses 3 per quarter. Scoring:
- Data-backed: answerable from current inputs. Reject otherwise.
- Decision-relevant: answering it changes what the writer does next quarter.
- Recency filter: don't re-ask last quarter's unresolved question without significant new data.
- User-prompted override: if writer invoked with specific question, force-include it.
- Portfolio coverage: across quarters, hit growth / product / voice axes.
Format per question
### Q{N}: {phrased as a real question, not a topic}
**Evidence**: What the numbers / corpus / audience actually say. Cite Growth Analyst report or specific posts.
**Reasoning**: Why the evidence leads to {answer}. Chain: A → B → C.
**Downside**: What specifically breaks if this recommendation is wrong.
**Recommendation**: Do X / Don't do X / Watch Y before deciding.
Guardrails
- Evidence-reasoning-downside triad is mandatory. Missing any → suppress the question.
- Never fabricate evidence. If the data doesn't exist, reject the question.
- Downside must be specific. "We lose time" is not a downside; "we lock in a topic the audience has outgrown" is.
- Recommendation is one line. Not a paragraph of hedging.
- 200-400 words per question. The full review has 3 questions at ~300 words each.
Related Skills
lyndonkl/skills/advisory-edit
testing
VerifiedTrustedCommunity
--- name: advisory-edit description: A strict advisory-only editing discipline for a writer who dictates ("speaks out") essays and wants help WITHOUT having their voice changed. The editor directs structure, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply" / "make that change" / "rewrite this." Produces a line-referenced, suggestion-only critique where every item is marked the writer's call. Four passes: structural, l
112SKILL.mdUpdated Jun 3, 2026
lyndonkl/strategist-voice
testing
VerifiedTrustedCommunity
Provides the house style for analyst-grade strategist writing — third-person register with sparing first-person, no em dashes, no "not X, not Y, not Z" negation cascades, numbered footnote citations rather than inline source parentheticals, specific opinion-signaling phrases, and topic-forward paragraph structure modeled on voice patterns observed in Damodaran's Musings on Markets and Thompson's Stratechery. Use when consolidating working notes into a finished long-form strategist or analyst report that must read as written by a senior human analyst rather than an AI assistant.
98SKILL.mdUpdated May 17, 2026
lyndonkl/markdown-to-pdf
testing
VerifiedTrustedCommunity
Renders a markdown report to a PDF using pandoc with xelatex (11pt serif body, 1-inch margins, numbered footnotes, formal heading hierarchy). Requires a one-time install of pandoc and a LaTeX engine on the user's machine — basictex on macOS or texlive-xetex on Linux. Does not attempt automatic install. Fails loudly with the exact install commands if pandoc or xelatex is missing on the user's PATH. Use when producing a finished strategist or analyst report PDF from a polished markdown source.
98SKILL.mdUpdated May 17, 2026
lyndonkl/worked-example-walkthrough
testing
VerifiedTrustedCommunity
Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.
94SKILL.mdUpdated May 10, 2026