676 skills · sorted by relevance
Find repeated engineering tasks and turn them into agent workflows with clear checks, stopping rules, and approval boundaries. Compare published workflows, adapt suitable examples, or review existing ones for weak verification and uncontrolled repetition.
Turn a vague intention into a concrete goal with clear scope, measurable success criteria, and evidence of completion. Check existing goals before creating one, so the agent has a specific outcome to pursue without duplicating active work.
Save working changes as local Git commits with messages that explain the outcome. Follow the project's commit style, select files explicitly, and split clearly separate changes into a few logical commits when appropriate.
Find and use skills, shared tools, and connected services available in an OpenWork organization. Match a requested outcome to an available capability, run it with the required parameters, and explain any connection or permission steps.
Read market details and public order prices directly from Polymarket. Match outcomes such as Yes or No to their token identifiers, then use the best buying and selling prices to calculate a midpoint.
Draft a project status report against stated milestones using recent Screenpipe activity and verified outcomes. Separate work performed from delivered and accepted results, summarize blockers and next actions, and cite dated sources with verification limits.
Analyze won and lost HubSpot deals by customer segment, competitor, deal value, and the stage before a loss. Group recorded loss reasons into themes and post a weekly Slack summary with concrete recommendations, leaving deal records unchanged.
Create a weekly engineering and product update from GitHub and Slack, combining shipped outcomes with contributor rankings, merged pull request counts, weekly changes, consecutive shipping weeks, and a thread for asynchronous team check-ins.
Use pointed workplace reminders inspired by 《置身钉内》 and 《置身钉外》 to examine reports, meetings, and delivery claims. Turn organizational concerns into concrete next steps and check completion against user outcomes and evidence.
Check estimated token usage against daily limits before and after each automated loop run. Switch to reporting only, exit early when required, and record run outcomes so repeated agent work stays within configured limits.
Help an agent run terminal commands, follow long-running jobs, retrieve logs, and cancel work. It explains result fields, execution deadlines, retained output, and operating-system differences so the agent can interpret command outcomes and choose appropriate tools.
Prepare a structured JSON handoff for bug fixes or pull request reviews. Capture outcomes, test evidence, change impact, publication status, and remaining work so the next person or workflow can understand what is complete and what remains.
Record how a legal matter ended, its final cost, differences from the original risk estimate, and lessons learned. Close active tracking while preserving the matter’s files and history for future reference.
Deploy ClawHub to production or publish a stable CLI release to npm. Check prerequisites for the exact commit, run the release workflow, and verify the deployed behavior or published version with traceable release evidence.
Review an agent's saved context and unread coordination messages at the start of a task. Summarize relevant assignments, move handled messages aside, and prompt the agent to preserve lasting decisions and outcomes before finishing.
Guide a development team from an assigned user outcome through implementation, testing, and handoff. It covers reproducing defects, checking behavior against requirements, involving design when needed, and reporting the exact changes, verification results, and remaining uncertainty.
Guide changes to RDD reviewer integrations through a shared Go contract, a common set of processing rules. Define adapter boundaries, validate result handling, and check that runtime migrations preserve existing review outcomes.
Prepare detailed reports before company earnings announcements. Organize market expectations, company guidance, key performance measures, possible outcomes, and questions for management, with clear source timestamps and explicit gaps in the available evidence.
Create and manage prediction markets on Solana, where participants trade YES or NO outcome tokens. Support includes direct peer bets, social media metrics, custom result authorities, market settlement, and redemption of winning positions.
Guides LoopX benchmark experiments through benchmark-toolkit, covering run management, comparisons under matched conditions, and analysis of agent action histories. It helps explain outcomes and efficiency while tracking source versions, score validity, and evidence boundaries.
Convert agreed goals, constraints, and success criteria into a Seed specification an agent can execute and verify. A quality review checks consistency and testable outcomes, with any suggested refinements left for the user to approve.
Estimate causal effects between exposures and outcomes using genetic variants as instrumental variables with TwoSampleMR. Implements IVW, MR-Egger, weighted median, and MR-PRESSO methods for robust causal inference from GWAS summary statistics. Use when testing whether an exposure causally affects an outcome using genetic instruments.
The English summary is being prepared. Showing the original description.
Build a Stockbee-style setup model book from momentum-burst screener candidates, then update 3-day and 5-day forward outcomes with MFE/MAE, stop-hit status, outcome tags, and cohort statistics. Use when the user wants to study Stockbee Momentum Burst examples, track failed candidates, build setup fluency, review A/B setup quality, or convert screener outputs into a learning loop rather than immediate trade signals.
The English summary is being prepared. Showing the original description.
Use when the user asks to "audit our launch plan", "are we ready to launch", or evaluate launch execution/outcomes; runs one typed RAMP preflight, execution, or outcome profile without mixing time horizons. Not for recording launch state — use launch-registry; not for running launch day — use launch-day-conductor. 发布就绪审计/RAMP分阶段评估/发布前放行
The English summary is being prepared. Showing the original description.