pm-value-anchor
Skill1 starsChanged 4 months agoMITView on GitHub
触发:需求价值/成功标准/取舍不清;不触发:范围规则不清→用pm-requirement-intake;读者判断→用audience-judgment-framing;输出:价值锚点
In this repository17 other files it gives its agents.
- audience-judgment-framingSkill
- embedded-prd-auditSkill
- freeze-readiness-checkSkill
- memory-export-summarySkill
- pm-demo-designSkill
- pm-design-absorptionSkill
- pm-devil-advocateSkill
- pm-embedded-prdSkill
- pm-prd-writerSkill
- pm-project-opsSkill
- pm-react-prototype-executionSkill
- pm-requirement-intakeSkill
- pm-requirement-reverse-auditSkill
- prototype-export-intakeSkill
- request-triageSkill
- rule-change-signalSkill
- state-auditSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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
- Distinctive: line 8
Use this skill before or during requirement intake when the value of a request is not explicit enough.
- Distinctive: line 14
Create a compact value anchor that clarifies:
- Distinctive: line 35
Do not force this skill when:
- Distinctive: line 61
If only 30% of the idea can be kept, what must remain?
- Very specific: line 84
Use before pm-requirement-intake when success is fuzzy.
- Very specific: line 86
Use with request-triage when workflow depth depends on value and risk.
- Very specific: line 87
Use with freeze-readiness-check when deciding whether a baseline is meaningful enough to preserve.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PM Value Anchor
Use this skill before or during requirement intake when the value of a request is not explicit enough.
The goal is to answer: if this work succeeds, what meaningful result should change?
Core Job
Create a compact value anchor that clarifies:
- who benefits
- what problem changes
- what success looks like
- what minimum version still counts as success
- what evidence could later prove or challenge the decision
This skill prevents the workflow from producing precise rules for a low-value or poorly framed request.
Use When
Use when:
- a request starts from a proposed solution instead of a clear problem
- success criteria are implicit
- a feature could be scoped many ways
- the request may be too broad for the current stage
- the user asks why a requirement matters or how to prioritize it
- a downstream PRD/demo/prototype risks becoming "complete but not compelling"
Do Not Use When
Do not force this skill when:
- the request is tiny and low-risk
- the value is already obvious and stable
- the user only needs a quick copy/config adjustment
- there is no product decision to clarify
Value Anchor Questions
Answer only what is useful for the request.
1. Beneficiary
- Who benefits directly?
- Who benefits indirectly?
- Which role feels the pain now?
2. Current Problem
- What is hard, slow, confusing, risky, or impossible today?
- What workaround exists?
- What fails if nothing changes?
3. Desired Outcome
- What should become easier, clearer, faster, safer, or more valuable?
- What user behavior or business result should change?
- What should reviewers be able to agree on?
4. Minimum Success
- If only 30% of the idea can be kept, what must remain?
- Which part proves the core value?
- Which part is polish or later expansion?
5. Evidence
- What data, user feedback, review result, usage signal, delivery milestone, or reduction in rework would support success?
- What evidence would show the idea was weak or scoped incorrectly?
Output Format
## Value anchor
- Target beneficiary:
- Current problem:
- Desired outcome:
- Minimum success version:
- Evidence to watch:
- Scope implication:
- Recommended next step:Relationship With Other Skills
- Use before
pm-requirement-intakewhen success is fuzzy. - Feed the value anchor into
pm-requirement-intakeas context. - Use with
request-triagewhen workflow depth depends on value and risk. - Use with
freeze-readiness-checkwhen deciding whether a baseline is meaningful enough to preserve.
Self-Check
Before finishing, check:
- Did I distinguish value from implementation detail?
- Did I define minimum success instead of listing every possible feature?
- Did I leave enough evidence hooks for later review?
- Did I avoid turning a small request into a strategy memo?
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.

