Frappucc1no/recall-loom / skills/recallloom
recallloom
FlaggedUse when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful progress across sessions. Works best for long-horizon, file-based projects and supports research writing, product document collaboration, software project coordination, and broader cross-functional project continuity.
references/profiles.md
View on GitHub# Profiles
Profiles are guidance layers built on top of the shared RecallLoom protocol.
They do not replace the core protocol.
## Default Rule
Use `general-project-continuity.md` by default.
Switch to a specialized profile only when the project shape is a high-confidence match.
If the project is mixed, ambiguous, or still changing shape, stay on the general profile.
## Current Profiles
- `general-project-continuity.md`
- `research-writing.md`
- `product-doc-collaboration.md`
- `software-project-coordination.md`
## How to Choose
Use this quick selector:
1. Is the project primarily driven by sources, claims, evidence, and long-form analytical writing?
Use `research-writing.md`.
2. Is the project primarily driven by PRDs, RFCs, strategy docs, scope decisions, or stakeholder-aligned product writing?
Use `product-doc-collaboration.md`.
3. Is the project primarily driven by engineering planning, spec-to-implementation coordination, or repo-level software project continuity?
Use `software-project-coordination.md`.
4. If none of the above is a high-confidence match, use `general-project-continuity.md`.
High confidence means the main artifact type, working style, and likely drift risks all line up clearly.
When choosing, look at:
- artifact type
- working style
- continuity risks
- evidence needs
## Profile Summary
- `general-project-continuity.md`
- default profile for mixed, cross-functional, or unclear long-running projects
- `research-writing.md`
- best when the hard problem is keeping claims, evidence, and section progress aligned
- `product-doc-collaboration.md`
- best when the hard problem is keeping scope, stakeholder context, and durable decisions aligned
- `software-project-coordination.md`
- best when the hard problem is keeping specs, implementation state, and project coordination aligned
## Shared vs Profile-Specific
Shared:
- file model
- write discipline
- stale retirement
- cold-start expectations
Profile-specific:
- evidence patterns
- artifact emphasis
- likely drift risks
- preferred review lens
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |