reduce-to-facts
Skill2 starsChanged 2 months agoMITView on GitHub
Use for dense or messy workplace source material - Slack threads, email chains, memos, transcripts, policy docs, vendor writeups, research notes, strategy notes, or customer escalations - before replying, deciding, escalating, or acting when context is long, ambiguous, stakeholder-sensitive, high-stakes, contradictory, or easy to misread. Use source-expanded mode only when the user explicitly asks to verify, fact-check, expand sources, support or refute claims, or use outside sources; not for simple catch-ups or straightforward reply drafting unless uncertainty needs to be preserved first.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brief-meSkill
- clear-askSkill
- decision-briefSkill
- follow-up-draftSkill
- meeting-to-actionsSkill
- status-updateSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
43 rules. About 0 are common, 42 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈42
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use this when the context is too long, ambiguous, stakeholder-sensitive, high-stakes, contradictory, or too important to act on safely from …
- Very specific: line 18
Do not use this for simple short threads where brief-me, clear-ask, or follow-up-draft can act directly.
- Distinctive: line 22
Default to a compact ledger with only the sections needed for the source.
- Distinctive: line 24
Use the full ledger only when the source is dense, high-stakes, contradictory, or the user explicitly asks for a full fact ledger.
- Distinctive: line 28
Use "None surfaced in the reviewed source" only when that absence is itself useful.
- Distinctive: line 40
Use only the useful subset of source-backed facts, assumptions, source gaps, stakeholder sensitivities, potential misreads, and the …
- Distinctive: line 42
Use the smallest useful output.
- Distinctive: line 44
Do not promote an assumption, inference, open question, proposed action, or stakeholder position into a fact, decision, commitment, owner, …
- Distinctive: line 47
Keep unresolved approvals, owners, timing, and blockers explicit.
- Distinctive: line 48
Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.
- Distinctive: line 52
Default to source-only mode.
- Distinctive: line 58
Use only the supplied source material.
- Distinctive: line 59
Do not verify externally.
- Distinctive: line 60
Do not treat supplied material as true by default.
- Distinctive: line 62
Use source anchors from the supplied material.
- Distinctive: line 66
Use only when explicitly asked.
- Distinctive: line 67
Keep the source-only ledger logic.
- Distinctive: line 68
Add outside evidence only where authorized.
- Distinctive: line 69
Do not pretend to have checked sources that were not actually checked.
- Distinctive: line 71
Do not use related evidence as proof of a specific claim.
- Distinctive: line 72
Do not collapse contested claims into facts.
- Distinctive: line 74
If tools are unavailable, say so and keep the claim unverified.
- Distinctive: line 91
Do not summarize loosely.
- Distinctive: line 92
Do not smooth over uncertainty.
- Distinctive: line 93
Do not invent missing support.
- Distinctive: line 94
Do not collapse facts, opinions, and assumptions.
- Distinctive: line 95
Do not upgrade "supported in substance" to "supported exactly."
- Distinctive: line 96
Do not write a reply by default.
- Distinctive: line 97
Do not recommend a decision by default.
- Distinctive: line 104
Create local anchors when the source does not provide them, such as line numbers, timestamps, speaker labels, file names, or section names.
- Distinctive: line 106
Treat "X said Y" as a fact about the statement, not proof that Y is true.
- Distinctive: line 109
Keep implications as constraints, not final recommendations.
- Distinctive: line 119
Use this table in source-expanded mode, or whenever you need to show which claims got stronger, weaker, contested, or unverified after …
- Distinctive: line 140
Keep evidence, interpretation, and persuasion separate.
- Distinctive: line 142
If a source step is rhetorical rather than evidentiary, label it as such.
- Distinctive: line 143
Do not dismiss the source.
- Distinctive: line 165
Do not combine multiple claims into one fact.
- Distinctive: line 166
Use direct source anchors when available: section, paragraph, timestamp, speaker, file name, page, or quoted phrase.
- Distinctive: line 168
If source anchors are unavailable, say so.
- Distinctive: line 180
Do not convert opinions into facts.
- Distinctive: line 206
Do not present inference as fact.
- Distinctive: line 238
Do not recommend a final decision unless the user explicitly asks.
- Distinctive: line 252
If a named downstream skill is unavailable in the host assistant, describe the next step in plain language instead of pretending the skill …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
reduce-to-facts
Purpose
Turn dense workplace source material into a fact ledger the user can trust before moving to a reply, decision, or action.
When to use
Use this when the context is too long, ambiguous, stakeholder-sensitive, high-stakes, contradictory, or too important to act on safely from a normal summary.
When not to use
Do not use this for simple short threads where brief-me, clear-ask, or follow-up-draft can act directly.
Output size rule
Default to a compact ledger with only the sections needed for the source.
Use the full ledger only when the source is dense, high-stakes, contradictory, or the user explicitly asks for a full fact ledger.
- Omit empty optional sections for compact outputs.
- For dense or high-stakes sources, include all major sections.
- Use "None surfaced in the reviewed source" only when that absence is itself useful.
For short inputs, include:
- Source scope
- Atomic facts
- Open questions
- Action-relevant implications
- Suggested next skill
Portable Output Contract
- Use only the useful subset of source-backed facts, assumptions, source gaps, stakeholder sensitivities, potential misreads, and the suggested next action.
- Use the smallest useful output.
- Label assumptions and preserve source gaps, source anchors, and confidence labels.
- Do not promote an assumption, inference, open question, proposed action, or stakeholder position into a fact, decision, commitment, owner, or deadline without new source support.
- Keep unresolved approvals, owners, timing, and blockers explicit.
- Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.
Source Mode
Default to source-only mode.
Switch to source-expanded mode only when the user explicitly asks to verify, fact-check, expand sources, support claims, refute claims, or use outside sources.
Source-Only Mode
- Use only the supplied source material.
- Do not verify externally.
- Do not treat supplied material as true by default.
- Separate directly stated claims from implied, assumed, or unsupported claims.
- Use source anchors from the supplied material.
Source-Expanded Mode
- Use only when explicitly asked.
- Keep the source-only ledger logic.
- Add outside evidence only where authorized.
- Do not pretend to have checked sources that were not actually checked.
- Distinguish exact support from support in substance.
- Do not use related evidence as proof of a specific claim.
- Do not collapse contested claims into facts.
- Include citations, links, or source anchors when supported.
- If tools are unavailable, say so and keep the claim unverified.
Inputs
- Long threads
- Dense memos
- Policy docs
- Vendor writeups
- Strategy notes
- Research notes
- Customer escalations
- Transcripts
- Similar source material
Guardrails
- Read before write.
- Do not summarize loosely.
- Do not smooth over uncertainty.
- Do not invent missing support.
- Do not collapse facts, opinions, and assumptions.
- Do not upgrade "supported in substance" to "supported exactly."
- Do not write a reply by default.
- Do not recommend a decision by default.
- Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.
- Preserve uncertainty when the source is ambiguous.
Process
- Identify the source scope first.
- Create local anchors when the source does not provide them, such as line numbers, timestamps, speaker labels, file names, or section names.
- Extract only source-supported claims.
- Treat "X said Y" as a fact about the statement, not proof that Y is true.
- Move weakly supported claims into Unsupported or Under-Supported Claims.
- Label reasoning beyond the source as Inference.
- Keep implications as constraints, not final recommendations.
Confidence Rubric
- High: directly stated with a clear anchor, or supported by multiple consistent anchors.
- Medium: directly stated but context is incomplete, wording is ambiguous, or only one source supports it.
- Low: implied, secondhand, weakly supported, or dependent on missing context.
Claim Status Table
Use this table in source-expanded mode, or whenever you need to show which claims got stronger, weaker, contested, or unverified after outside evidence.
| Claim | Status | Evidence | Caveat |
Status meanings:
- Supported exactly: the source says this directly, with matching wording or a direct equivalent.
- Supported in substance: the source backs the core point, but the exact wording is broader or sharper than the source.
- Partly supported: part of the claim is source-backed, but part of it is not.
- Contested: sources disagree.
- Overstated: the claim reaches beyond what the evidence can support.
- Unsupported: no source support found.
- Refuted: available evidence cuts against the claim.
- Unverified: not checked, or not enough evidence was found.
Do not upgrade "supported in substance" to "supported exactly."
Rhetorical Leaps
- Show the move from exact wording to broader implication.
- Keep evidence, interpretation, and persuasion separate.
- A quote or denial can support a concern without supporting the strongest version of that concern.
- If a source step is rhetorical rather than evidentiary, label it as such.
- Do not dismiss the source; explain the leap.
Fact Ledger
Source Scope
- Source(s) reviewed:
- Source type:
- Time period covered:
- Known limitations:
- Missing context:
Atomic Facts
Use a table:
| ID | Fact | Source anchor | Confidence | Notes |
Rules:
- Facts must be atomic.
- Do not combine multiple claims into one fact.
- Use direct source anchors when available: section, paragraph, timestamp, speaker, file name, page, or quoted phrase.
- Confidence values: High / Medium / Low.
- If source anchors are unavailable, say so.
Attributed Opinions / Positions
Use a table:
| ID | Who/Source | Position | Basis | Confidence |
Rules:
- Opinions must be attributed.
- Do not convert opinions into facts.
- Include stakeholder positions, preferences, concerns, and proposed direction.
Unsupported or Under-Supported Claims
Use a table:
| ID | Claim | Why unsupported | Evidence needed |
Rules:
- Include claims that sound important but lack source support.
- Include obvious-sounding assumptions if they are not actually supported by the provided source.
Inferences
Use a table:
| ID | Inference | Based on | Risk if wrong |
Rules:
- Inferences are allowed, but must be explicitly labeled.
- Link each inference to facts or source material.
- Do not present inference as fact.
Contradictions / Tensions
Use a table:
| ID | Conflict | Sources involved | Needs resolution |
Rules:
- Include hard contradictions and softer tensions.
- Include cases where one section implies readiness but another suggests a blocker.
Open Questions
Use a table:
| ID | Question | Why it matters | Likely owner |
Rules:
- Focus on questions that block action, decision, reply, or confidence.
Action-Relevant Implications
Use bullets.
Rules:
- These are implications, not decisions.
- Do not recommend a final decision unless the user explicitly asks.
- End this section with: "Do not treat these implications as final decisions."
Suggested Next Skill
Recommend one downstream skill:
clear-askif the next problem is clarifying what someone wants.decision-briefif the next problem is choosing between options.status-updateif the next problem is communicating what changed.follow-up-draftif the next problem is replying safely.meeting-to-actionsif the next problem is extracting owners/actions.brief-meif the user needs a fast catch-up.
If a named downstream skill is unavailable in the host assistant, describe the next step in plain language instead of pretending the skill can be invoked.
Success Standard
The user should be able to trust the fact ledger as a clean substrate for the next step. In source-expanded mode, the user should also be able to see which claims got stronger, weaker, stayed contested, or remained unverified after outside evidence was checked.
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.

