history
Skill304 starsChanged 2 months agoMITView on GitHub
Browse and search past analyses from the knowledge system's analysis archive. Use this skill whenever the user invokes `/history` or variants like `/history search=X`, `/history {id}`, `/history --all`, `/history dataset=X`, or asks questions about their analytical work history such as "what have I analyzed before?", "what analyses have I run?", "show me past work", "show my history", "what have we looked at?", "what questions have I answered?", "can I see my analysis history?", "list my analyses", "what did I work on last week?", "have I analyzed X before?", "find analyses about Y", or mentions reviewing prior analyses, checking if similar work was already done, needing context on previous findings, or wants to build on past work. This skill also applies automatically at session start when you need context on the user's analytical history to inform current work. When displaying history, ALWAYS filter to the active dataset unless the user explicitly requests --all or dataset={id}.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- nguyenthanhtat/screen1-claudetheir own version, first seen Nov 1, 2026
- ARCASSystems/FounderOStheir own version, first seen Oct 24, 2026
- pche-broken-artist/forge-of-thoughttheir own version, first seen Oct 13, 2026
- ayrshare/ayrshare-social-media-api-claude-plugintheir own version, first seen Oct 13, 2026
- Kooboo/Koobootheir own version, first seen Oct 13, 2026
- bradautomates/second-braintheir own version, first seen Oct 9, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- cosmosgl/graph★ 1.3ksame name
- Kooboo/Kooboo★ 345same name
- QuantConnect/Documentation★ 268same name
- bradautomates/second-brain★ 217same name
- Deibler/edmund-harness★ 24same name
- ayrshare/ayrshare-social-media-api-claude-plugin★ 19same name
- ay-bh/chat-history★ 15same name
- pche-broken-artist/forge-of-thought★ 14same name
- huiruru/ecoguilt★ 9same name
- ARCASSystems/FounderOS★ 7same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository65 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- always-compareSkill
- analysis-designSkill
- analyst-coreSkill
- archaeologySkill
- archive-analysisSkill
- auth-preflightSkill
- businessSkill
- causalSkill
- chart-to-driveSkill
- close-the-loopSkill
- codex-reviewSkill
- compare-datasetsSkill
- connect-dataSkill
- connect-snowflakeSkill
- context-compareSkill
- context-traceSkill
- data-inspectSkill
- data-mapSkill
- data-profilingSkill
- data-quality-checkSkill
- datasetsSkill
- distribution-profilerSkill
- evalSkill
- evaluate-graderSkill
- experiment-briefSkill
- experimentSkill
- exploreSkill
- exportSkill
- forecastSkill
- google-doc-exportSkill
- google-slides-exportSkill
- guardrailsSkill
- improve-contextSkill
- knowledge-bootstrapSkill
- log-correctionSkill
- maintain-contextSkill
- metric-specSkill
- metricsSkill
- monitor-evalsSkill
- notion-exportSkill
- paceSkill
- patternsSkill
- question-framingSkill
- question-routerSkill
- reliabilitySkill
- resume-pipelineSkill
- run-pipelineSkill
- runsSkill
- score-analysisSkill
- session-handoffSkill
- setup-dev-contextSkill
- setup-notionSkill
- setupSkill
- setup-slackSkill
- setup-snowflakeSkill
- srm-checkSkill
- stakeholder-communicationSkill
- stress-testSkill
- switch-datasetSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
When framing a new question, to check if similar analysis exists
- Distinctive: line 29
If empty: "No analyses archived yet.
- Distinctive: line 32
IMPORTANT: Before filtering results, determine the active dataset:
- Very specific: line 34
Read .knowledge/active.yaml to get the active dataset ID
- Very specific: line 35
If --all flag is present: skip filtering, show all datasets
- Very specific: line 36
If dataset={id} is specified: filter to that dataset
- Distinctive: line 57
Search across: title, question, key_findings, tags (case-insensitive)
- Very specific: line 59
If no matches: "No analyses match '{term}' in {dataset_name}.
- Very specific: line 69
If recent analysis was partial: "This analysis was incomplete.
- Distinctive: line 73
Archive file missing: Create empty index
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: History
Purpose
Browse and search past analyses from the analysis archive. Helps users recall what they've analyzed before, find prior findings, and build on previous work.
When to Use
- User says
/historyor "what have I analyzed before?" - At session start, to provide context on prior work
- When framing a new question, to check if similar analysis exists
Invocation
/history — list recent analyses (last 10)
/history {id} — show full details for a specific analysis
/history search={term} — search by title, question, or tags
/history --all — list all analyses across all datasets
/history dataset={id} — filter to a specific dataset
Instructions
Step 1: Load Archive
- Read
.knowledge/analyses/index.yaml - If empty: "No analyses archived yet. Complete an analysis and it will appear here."
Step 2: Determine Active Dataset (Critical)
IMPORTANT: Before filtering results, determine the active dataset:
- Read
.knowledge/active.yamlto get the active dataset ID - If
--allflag is present: skip filtering, show all datasets - If
dataset={id}is specified: filter to that dataset - Otherwise: filter to active dataset only
This ensures users see relevant analyses for their current working context by default.
Step 3: Execute Command
List recent (/history):
- Filter to active dataset (unless
--allflag present) - Sort by date descending
- Show last 10 as a table: date, title, level, key finding count, dataset
- Show total count: "Showing 10 of {total} analyses for {dataset_name}." (or "across all datasets" if --all)
Show specific (/history {id}):
- Find entry by ID in index
- Display: title, date, question, level, all key findings, metrics used, agents used, output files, tags, confidence, recommendations
- If output files exist, offer: "Want to review the full analysis? The deck is at {path}"
Search (/history search={term}):
- Filter to active dataset first (unless
--allordataset={id}specified) - Search across: title, question, key_findings, tags (case-insensitive)
- Display matching entries as a table
- If no matches: "No analyses match '{term}' in {dataset_name}. Try broader terms or use
--allto search across all datasets."
All datasets (/history --all):
- Include dataset_id column in output
- Sort by date descending across all datasets
Step 4: Contextual Suggestions
After displaying history:
- "Want to re-run this analysis with fresh data?"
- "Want to build on finding #{n}?"
- If recent analysis was partial: "This analysis was incomplete. Resume with
/resume-pipeline."
Edge Cases
- No active dataset: Show all analyses or prompt to connect
- Archive file missing: Create empty index
- Analysis output files deleted: Note "output files no longer available"
- Very long history (>100): Paginate, show 20 at a time
Why This Matters
Dataset filtering ensures users see relevant analyses for their current working context. A user analyzing one dataset shouldn't see unrelated-dataset analyses by default — it creates noise and makes it harder to find relevant prior work. The --all flag is available when cross-dataset comparison is needed.
Contextual offers ("Want to review the full analysis?") help users take action on the information. Simply listing file paths isn't enough — explicitly offering next steps makes the history actionable.
Consistent table format allows quick scanning. Users browse history to find patterns, check if work was done before, or locate specific analyses. Tables are faster to scan than prose paragraphs.
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.

