Individual skill
pov
Use when asked to judge whether to adopt, switch, reject, or revisit technology, library, pattern, or architecture, or a second opinion. Not for scoping: use brainstorm. Not for forks: use decide.
.devin/skills/pov/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
- Local scripts
- 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
- engineering 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 · 8,557 bytesSKILL.mdcore · 8,557 bytesSKILL.mdcore · 8,557 bytesSKILL.mdcore · 8,557 bytesSKILL.mdcore · 8,557 bytesagents/openai.yamlasset · 193 bytesreferences/agents-external-evidence-researcher.mddoc · 2,536 bytesreferences/agents-precedent-activity-scout.mddoc · 2,949 bytesreferences/agents-project-grounding-scout.mddoc · 4,473 bytesreferences/boundaries.mddoc · 2,870 bytesreferences/intake.mddoc · 3,796 bytesreferences/invocation.mddoc · 3,045 bytesreferences/method.mddoc · 5,745 bytesreferences/report.mddoc · 1,763 bytes
Read excerpt
# Pov
## Contract
| Field | Bound contract |
|---|---|
| Trigger | Explicit invocation to judge a technology, library, pattern, platform, or architecture against the current project, or to give a mid-session second opinion. |
| Authority | Reversible local: writes only a run-specific scratch directory, the project-profile cache under `/tmp/odin/repo-profile/`, and an optional local report at a user-supplied path; rollback is deleting those artifacts. No project-file, VCS, credential, paid, or remote mutation. |
| Side effect | Cache a question-agnostic repository profile and scout dossiers locally; return the verdict in chat by default. Delete the run scratch directory, any cache entry created by this run, and any optional report to roll back local writes. |
| Done | A compact graded verdict passes both evidence floors, states its reversibility tier and confidence, cites the decisive evidence, records conditions and a tier-sized reversal trigger (Tier 2/3 only), and gives the computed next action; or an exact Hold result identifies the failed floor. |
## Inputs
Required: the subject to judge and the intended decision (adopt, migrate, compare, determine fit, reject, or revisit). For a mid-session invocation, take the question and claims to verify from the surrounding conversation, but do not treat them as evidence. If the intent is ambiguous, obtain one answer before research.