parallel-investigation
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analysis work. Provides structured phases for problem decomposition, thread assignment, sync points with Continue/Pivot/Converge decisions, and final report synthesis.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates what the skill does (coordinate parallel investigation threads with structured phases), when to use it (production incidents, complex bugs, multi-system failures where root cause is unclear), and how it's distinct from simpler debugging approaches. It uses third person voice consistently and includes rich, natural trigger terms that users would actually say when facing these scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'coordinates parallel investigation threads', 'explore multiple hypotheses or root causes', 'problem decomposition', 'thread assignment', 'sync points with Continue/Pivot/Converge decisions', and 'final report synthesis'. These are concrete, well-defined actions. | 3 / 3 |
Completeness | Clearly answers both 'what' (coordinates parallel investigation threads, provides structured phases for decomposition, thread assignment, sync points, and report synthesis) and 'when' (explicit 'Use when' clause covering production incidents, slow API performance, multi-system failures, complex bugs with unclear root cause, when serial troubleshooting is too slow, or when multiple investigators can divide work). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'debugging production incidents', 'slow API performance', 'multi-system integration failures', 'complex bugs', 'root cause', 'troubleshooting', 'root-cause analysis'. These cover a good range of natural language a user would use when facing these problems. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: parallel investigation coordination with structured phases and sync points. The emphasis on multiple simultaneous hypotheses, Continue/Pivot/Converge decisions, and multi-investigator coordination distinguishes it clearly from general debugging or incident response skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured coordination framework for parallel investigations with clear phases, decision points, and sync mechanisms. Its main weakness is that it reads more like a process methodology document than an actionable skill — it lacks concrete, executable commands or tool-specific guidance that Claude could directly apply. The workflow clarity is strong with explicit decision frameworks and validation checkpoints, but the content could be more concise and better distributed across supporting files.
Suggestions
Add concrete, executable examples — e.g., actual diagnostic commands for each thread type (database: specific SQL EXPLAIN queries; infrastructure: specific monitoring tool commands; application: profiling commands) rather than abstract descriptions.
Split the templates (Thread Log, Final Report, Communication Protocol) into a separate TEMPLATES.md file and reference it from the main skill to improve progressive disclosure and reduce the monolithic feel.
Trim the 'Core Principle' section and reduce redundancy between the Phase 3 thread log template and the Phase 4 sync point summary — they overlap significantly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some unnecessary verbosity. The 'Core Principle' section states the obvious, and several templates (thread log, sync point agenda, final report) are somewhat redundant with each other. The content could be tightened by ~30% without losing clarity. However, it doesn't over-explain basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides structured templates and frameworks but remains largely abstract — it describes a process methodology rather than giving executable commands or concrete code. The examples (like the API slowness scenario) are illustrative but not copy-paste actionable. There are no actual diagnostic commands, scripts, or tool invocations that Claude could directly execute. | 2 / 3 |
Workflow Clarity | The five-phase workflow is clearly sequenced with explicit sync points and a well-defined decision framework (Continue/Pivot/Converge). The convergence phase includes validation steps (other threads verify findings). The decision framework table and time management section provide clear checkpoints. The feedback loop of sync points with explicit decision criteria is well-articulated. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no bundle files. While it references other skills at the bottom (debugging/root-cause-analysis, hypothesis-testing, handoff-protocols), the main content is all inline. The report templates and communication protocols could be split into separate reference files. For a skill of this length (~150 lines of substantive content), some separation would improve navigability. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rohitg00/skillkit
- Commit
a9e5c83
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.