Individual skill
figure-it-out
Use when non-trivial work should run a matched playbook to verified real-surface completion, or a bespoke workflow when none fits. Not for remote, credential, publish, deploy, or irreversible changes.
.devin/skills/figure-it-out/SKILL.md
Source commit b0e8ce89a19fac880251dc3ea1babfeb4503a4fe
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 55
- Repository last updated
- Sep 28, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- odd Repository topic
- odin Repository topic
- outline Repository topic
- outlines Repository topic
- coding-paradigm Repository topic
- outline-driven-development Repository topic
- claude-plugins Repository topic
- codex-cli Repository topic
- gemini-cli-extensions Repository topic
- outline-driven Repository topic
- operations Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 9,206 bytesSKILL.mdcore · 9,206 bytesSKILL.mdcore · 9,206 bytesagents/openai.yamlasset · 197 bytesreferences/playbooks.mddoc · 8,772 bytes
Read excerpt
# Figure it out
## Contract
| Field | Bound contract |
|---|---|
| Trigger | Execute a non-trivial task by classifying it against the 23-playbook index and running the matched playbook end-to-end, or design a bespoke execution workflow when no playbook fits. |
| Authority | Reversible local: actions run in the working tree with version control as rollback, and the bespoke workflow writes only named local artifacts built for this task, each with its rollback path stated before it is written. Human-gated: preview every remote or irreversible action (push, PR creation or any other PR workflow mutation, release, deployment, credential use, branch or worktree deletion) with its exact consequence and obtain explicit human approval per action before it; approval for one does not authorize another. |
| Side effect | The matched playbook's or the bespoke workflow's actions execute in the working tree; agents, worktrees, and PR workflow operations are dispatched as the matched playbook requires; bespoke changes stay limited to the local artifacts named in the workflow. |
| Done | A matched playbook's required actions are completed per its contract in `references/playbooks.md` and its real-surface done check passes: the observation the playbook names as completion proof is made on the surface the user will actually use, not substituted by compilation, a worker report, a checked box, or source inspection; a bespoke run's falsifiable predicate is verified on the real product with a reviewable trail. |
## Inputs
- The task to execute; include the falsifiable success predicate when no playbook fits. Required.