research
FeaturedAnswer a bounded question with current cited evidence. Triggers: "research", "investigate", "find evidence".
AI & Automation 414 stars
40 forks Updated today Apache-2.0
Install
Quality Score: 96/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Research
Answer one bounded question with current evidence. Research informs a caller;
it does not select work, approve a plan, mutate lifecycle state, or decide what
happens next.
## Contract
1. State the question, decision it informs, scope, non-goals, and evidence
required for a useful answer.
2. Search the smallest relevant local sources. For changing external facts,
use current primary sources.
3. Verify structural or semantic-search leads against authoritative content.
4. Separate observation, inference, contradiction, and unknown.
5. Lead with the answer and cite every load-bearing claim.
6. Report unchecked scope and stop.
Use the current agent inline by default. Parallel readers or alternate runtimes
are optional execution choices only when the caller authorizes them. Prior
research, CASS, MS, codebase recon, and pattern mining are advisory sources,
not required phases.
## Commit-level citation for code claims
A claim about what code does cites the commit it was observed at, plus
file:line — code moves, and a citation without a revision decays silently into
a claim about a repository that no longer exists. For the working tree, record
the current HEAD and whether the cited file carries uncommitted changes. The
named failure mode is the floating citation: a path and line that resolved
when written, drifted after a refactor, and now lends false authority to a
stale answer. A reader must be able to run `git show <commit>:<path>` and see
the cited lines; a ...
Details
- Author
- boshu2
- Repository
- boshu2/agentops
- Created
- 8 months ago
- Last Updated
- today
- Language
- Go
- License
- Apache-2.0
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
AI & Automation Listed
research
Research technical questions, APIs, libraries, standards, security guidance, compatibility, and current product behavior using authoritative primary sources and explicit evidence. Use when a task depends on external, niche, disputed, version-sensitive, or recently changed facts, or when the user asks to research, compare, verify, or cite technical information. Do not use when the answer is established entirely by the local repository or a simple stable fact.
1 Updated today
dayfinggg AI & Automation Listed
research
External web research mode.
38 Updated today
lemoncrow-lab AI & Automation Solid
researcher
Research external libraries, APIs, and best practices, with evidence.
123 Updated today
antonbabenko