Matt Pocock / skills/productivity/grilling/SKILL.md
Grilling
A decision interview that groups questions by dependency and makes unresolved assumptions visible before work starts.
Source reviewed · reviewed · Named sources were inspected. No runtime results are established by this label.
01 / Task fit
Where it may help.
These are intended uses indicated by the upstream material. They are not measured outcomes.
- Scoping a feature with unresolved permission or delivery decisions
- Testing a plan before turning it into implementation tasks
What it is
Grilling gives an agent a structure for stress-testing a plan. It maps decisions and asks the questions that can be answered with what is already known. It is useful when a vague request hides choices about users, permissions, scope or delivery.
Why you might use it
Use it when the cost of building the wrong thing is higher than the cost of a focused interview. Its value is a clearer set of decisions and open questions; it does not prove that the eventual plan is correct.
Put it in context.
Illustrative requests and outputs to review. These examples are separate from the recorded evaluation below.
Define a customer export
Example request
Grill this plan: add a CSV export for account administrators. Start with who can export which records, then ask about format and delivery. Use only the synthetic requirements I provide.
What to look for. A decision tree that settles record access before fields, delivery and retention.
Before you rely on it. A recommendation is still a proposal. Review access and retention decisions before implementation.
Choose an evaluation workflow
Example request
Stress-test a process for reviewing 200 synthetic support answers. Separate decisions about the rubric, reviewer assignment and disagreement handling.
What to look for. A sequence of dependent decisions, with factual gaps assigned to bounded research.
Before you rely on it. Do not let research cross into private customer material without an explicit data scope.
02 / Setup & access
What it asks of your environment.
Requirements
- An agent that can load the instruction file and retain the interview context.
- A user available to settle consequential decisions. Subagent and filesystem/search tools are needed only for delegated fact finding.
- No skill-specific account, API key, language runtime or installation helper is specified.
Permissions & data access
- Conversation access; optional project reads or public research through the host agent.
- Delegated work inherits the host tools and permissions; the source gives no separate sandbox.
Instructions alone do not enforce a sandbox. The agent host, connected tools and approvals determine what the skill can actually read, change or send.
03 / Things to check
Security concerns & practical limits.
These concerns follow from the reviewed sources. They describe possible exposure or required review; they are not confirmed vulnerabilities.
Review before use
Fact finding can widen tool access
The instructions delegate missing facts to a subagent. Limit that subagent to the relevant project and permitted sources; the skill does not enforce access controls.
Review before use
Recommendations can steer decisions
Every question includes a recommended answer, and yes accepts it. Ask the agent to separate evidence from assumptions and keep unresolved choices visible.
Limits and nuances
- Instruction-only entrypoint: no executable helper was identified in the reviewed skill. No interview, model comparison, subagent research, file search or implementation workflow was run.
- The review covers this entrypoint and repository license. Host permissions, context retention, question quality and decision completeness were not evaluated.
04 / Review record
What we checked. What’s still open.
Recorded review scope
- skills/productivity/grilling/SKILL.md
- LICENSE
Not tested or established
- Instruction-only entrypoint: no executable helper was identified in the reviewed skill. No interview, model comparison, subagent research, file search or implementation workflow was run.
- The review covers this entrypoint and repository license. Host permissions, context retention, question quality and decision completeness were not evaluated.
- Review date
- Source revision
49dd158d1076134a641b33efb035946536778336- Our relationship
- Explored. Investigated through the recorded review. No use or replication is claimed.
Upstream content can change after review. A repository revision identifies source scope; it does not prove that every script, dependency or runtime behavior was tested. How freshness is handled.
Recorded evaluation / Source review
Results with their limits attached.
Completed 5 bounded source checks covering requirements, workflow boundaries and practical security concerns. No skill workflow was executed.
- Passed
- 5
- Failed
- 0
- Total recorded
- 5
These counts refer to the cases in this report. They are not a benchmark against other skills. A source review does not establish runtime behavior.
Read the evidence reportThe report provides the case definitions, observations and baseline scope. Missing baselines or untested behaviors remain limitations.
Recorded environment
- Pinned public UTF-8 sources; exact Git blob contents fetched through GitHub and recorded with SHA-256.
- Windows 11; Python 3.12.10 source-condition verification. No account, private document or live business data.
Recorded commands (2)
Commands document this evaluation. They are not setup instructions for your environment.
Read each pinned file listed in sourceManifest.python build-guide-reviews.py — verify the recorded source conditions and reconcile report counts.Findings from this evaluation
Needs attention
Fact finding can widen tool access
The instructions delegate missing facts to a subagent. Limit that subagent to the relevant project and permitted sources; the skill does not enforce access controls.
Needs attention
Recommendations can steer decisions
Every question includes a recommended answer, and yes accepts it. Ask the agent to separate evidence from assumptions and keep unresolved choices visible.
Observation
Canonical skill, separate from grill-me
The reviewed entrypoint is grilling. A different directory alias is not evidence of this skill being used, and its installation count is not transferred here.
Evaluation limitations
- Instruction-only entrypoint: no executable helper was identified in the reviewed skill. No interview, model comparison, subagent research, file search or implementation workflow was run.
- The review covers this entrypoint and repository license. Host permissions, context retention, question quality and decision completeness were not evaluated.
05 / Reuse & discovery
License, attribution & popularity.
MIT
Repository MIT license text inspected at this revision. Preserve its copyright and permission notice when redistributing covered source; separate dependencies and services can have their own terms.
Why it is in this collection
skills.sh displayed 941.2K installs for this named skill on the observation date. Rounded directory telemetry; not verified unique users, a quality score or measured growth.
941,200 skill installs on skills.sh
- Scope
- Directory listing for mattpocock-grilling; not the whole repository
- Observed
- Time window
- Individual listing says Installs; reporting window not independently established
Popularity and inclusion do not establish quality, compatibility or security. Counts belong to their named metric and date; they are not a current ranking.
Dated discovery signal
Discovery snapshots.
5,700 skill installs on skills.sh · Visible tab: Trending (24h); page title: This Week · board position 52
Observed . Scope: Canonical grilling listing in the directory Trending board.
Rounded 5.7K displayed at board position 52. The title and tab give different windows; this single snapshot is not independently verified growth or unique-user adoption.
Snapshot source ↗06 / Follow the evidence
Go to the original.
- Pinned skill instructions github.com
- Pinned repository license github.com
- Dated directory popularity context www.skills.sh
- Dated directory trending snapshot; window ambiguity disclosed www.skills.sh
IonBin’s source notes are independent assessments. Upstream authors retain their work and attribution. This page does not install or execute the skill.