persist
Skill2 starsChanged 7 months agoMITView on GitHub
Store your findings, analysis, or other outcomes for future reference. Use when user asks you to do something that does not explicitly mention planning but clearly does not involve taking action yet e.g. analysing or investigating something.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- synaptiai/agent-capability-standardtheir own version, first seen Nov 1, 2026
- broomva/skillstheir own version, first seen Jun 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- synaptiai/agent-capability-standard★ 6same name
- broomva/skills★ 4same name
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 repository23 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- .copilot/copilot-instructions.mdCopilot instructions
- ahaSkill
- explain-prSkill
- fetch-planSkill
- generate-pr-descriptionSkill
- grill-meSkill
- improve-a-planSkill
- improve-codebaseSkill
- planning-modeSkill
- planningSkill
- research-modeSkill
- review-prSkill
- rust-bevy-standardsSkill
- rust-bevy-test-conventionsSkill
- rust-standardsSkill
- tddSkill
- unslopSkill
- update-agentsSkill
- update-planSkill
- update-skillsSkill
- write-a-skillSkill
- wtfSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 11 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
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
- Very specific: line 27
No output: use local-ai-folder-markdown, the default for both skill groups
- Distinctive: line 30
Read only that group's implementation file, and follow it whenever this skill creates or updates a document.
- Distinctive: line 36
Before doing any work, determine whether the user's request is primarily about understanding or documenting existing code in the current …
- Very specific: line 47
Treat it as the topic/subject to persist — use it to derive {topic} and proceed to Step 3.
- Distinctive: line 54
Use the summary as the content to persist.
- Very specific: line 58
Check whether this skill is being invoked within the context of an existing plan (i.e.
- Distinctive: line 79
Create the document containing the outcome of your work (analysis, findings, comparison, etc.).
- Distinctive: line 82
Use visualisations (tables, diagrams, lists) where they add clarity but make sure they are in-lined in the output (e.g.
- Distinctive: line 83
If you consulted external resources (URLs, API docs, RFCs, etc.), include a Resources section at the end of the document listing them with …
- Distinctive: line 87
If you continue investigating or learning new things in this conversation after the initial write:
- Distinctive: line 89
Update the research document after each substantive discovery or conclusion
- Distinctive: line 90
Don't wait until the conversation ends — write incrementally as you learn
- Distinctive: line 91
Add new sections, update existing analysis, or note contradictions as they emerge
- Distinctive: line 92
If the document structure no longer fits the findings, restructure it
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Core idea
- Context window = RAM (volatile, limited)
- Anything important gets persisted.
Persistence
A persistence implementation decides where and how output is stored. This skill writes to one of two skill groups, decided in Step 3:
| Output | Skill group | Implementation file |
| Research documents | research | ./persistence/{implementation}.md |
| Documents inside an existing plan | plans | ../planning/persistence/{implementation}.md |
Once Step 3 has picked the group, find the setting, replacing {group} with research or plans:
R="$(git rev-parse --show-toplevel 2>/dev/null)/.ai/config.properties"; { cat "$R" ~/.ai/config.properties | grep '^persistence\.{group}[[:space:]]*=[[:space:]]*[^[:space:]]'; cat "$R" ~/.ai/config.properties | grep '^persistence[[:space:]]*=[[:space:]]*[^[:space:]]'; } 2>/dev/null | head -1 | tr -d ' \t\r'- No output: use
local-ai-folder-markdown, the default for both skill groups persistence.{group}={value}orpersistence={value}: use{value}. If the group's implementation file does not exist for{value}, tell the user the{group}skill group has no{value}implementation and uselocal-ai-folder-markdown
Read only that group's implementation file, and follow it whenever this skill creates or updates a document.
Workflow
Step 1: Determine task type
Before doing any work, determine whether the user's request is primarily about understanding or documenting existing code in the current repository.
- If yes → invoke the
research-codebaseskill instead. Do not continue with this skill.- Examples: "how does the auth flow work?", "document the payment service", "explain the middleware chain", "what classes handle X?"
- If no → continue with Step 2.
- Examples: no argument or "analyse this RFC", "summarise the compliance requirements", "investigate options for a new library", "compare approaches for X"
Step 2: Resolve the argument
If an argument was provided:
- Treat it as the topic/subject to persist — use it to derive
{topic}and proceed to Step 3.
If no argument was provided:
- Summarise the conversation since the last persistence event (i.e. since the last invocation of
persist,planning,planning-mode,research-mode, or any other skill that persists output). If no such event exists, summarise the entire conversation. - The summary must be structured around learnings, insights, and decisions — not a chronological account of what was said. Extract the substance: what was established, what was ruled out, what trade-offs were identified, what conclusions were reached.
- Derive
{topic}from the subject matter of that conversation segment. - Use the summary as the content to persist.
Step 3: Determine output location
Check whether this skill is being invoked within the context of an existing plan (i.e. you are aware of/working on a plan created by the planning or planning-mode skill).
Within an existing plan:
- Store output as a dated document
{yyyy-mm-dd} {topic}in that plan, following the plans implementation (see Persistence)
Standalone (no existing plan):
- Store output as a research document
{yyyy-mm-dd} {topic}, following the research implementation (see Persistence)
Where:
{yyyy-mm-dd}is today's date{topic}is an extremely succinct name of the topic in kebab-case
Step 4: Do the work
Conduct the research, analysis, or investigation the user requested.
Step 5: Persist findings
Create the document containing the outcome of your work (analysis, findings, comparison, etc.). Write the content in Markdown; the persistence implementation decides how it is stored.
- Structure the document in whatever way is most appropriate for the task
- Use visualisations (tables, diagrams, lists) where they add clarity but make sure they are in-lined in the output (e.g. only markdown in .md files)
- If you consulted external resources (URLs, API docs, RFCs, etc.), include a Resources section at the end of the document listing them with brief descriptions
Step 6: Keep findings current
If you continue investigating or learning new things in this conversation after the initial write:
- Update the research document after each substantive discovery or conclusion
- Don't wait until the conversation ends — write incrementally as you learn
- Add new sections, update existing analysis, or note contradictions as they emerge
- If the document structure no longer fits the findings, restructure it
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.

