Skip to content

rse/ase / plugin/skills/ase-task-research

ase-task-research

Verified

Research a topic in depth for the current or given task plan, by combining Internet/Web search with a grounding in the source artifacts of the project, and append the resulting research report to the "research" attachment of the task, optionally refining the plan by its recommendations. Use when the user wants to "research", "investigate", or "look into" a topic for a "task" or "plan".

@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md

$ARGUMENTS

@${CLAUDE_SKILL_DIR}/../../meta/ase-format-task.md @${CLAUDE_SKILL_DIR}/../../meta/ase-format-meta.md

Procedure

  1. Determine Task and Topic:

    1. Set initially, with any leading and trailing whitespace stripped. Inherit the always existing , , and from the current context. Do not output anything.

    2. React on task and/or topic:

      • If matches the regexp ^[a-zA-Z0-9#][a-zA-Z0-9#_-]*$, or has the format <id/>: or <id/>: <text/> where matches this regexp: set (or to itself for the first form) and to (or to empty for the first two forms), call the ase_task_id(id: "<ase-task-id/>", session: "<ase-session-id/>") tool of the ase MCP server to switch the task, and then only output the following :

      • Otherwise, only output the following :

    3. Treat as a comma-separated list of backend tokens. The getopt parser validates only the first token, so you MUST validate each remaining token yourself against the allowed set all, perplexity, brave, exa, websearch. If any token is not in this set, bind to that offending token, then only output the following and then immediately STOP processing the entire current skill:

      A backend is selected if all is in OR that backend's own name is in .

    4. Load: call the ase_task_load(id: "<ase-task-id/>", tag: true) tool of the ase MCP server -- with the variant argument defaulting to source and the attachments argument defaulting to elided -- and set to its text output field without the trailing <task-plan-tag> delimiter line, and to the content of that line. If is empty or starts with ERROR: or WARNING:, only output the following and then immediately STOP processing the entire current skill:

  2. Research the Web:

    1. Derive two to four focused, complementary search queries from -- like its established practices and standards, its typical solutions, libraries, or patterns, and its known pitfalls. Each query is a self-contained summary of an aspect of and MUST NEVER carry confidential project internals: no file paths, no symbols or identifiers, and no other names taken from the project or from , as the queries leave the project towards foreign search services. Do not output anything.

    2. Invoke the following tool once per query of and per selected backend, emitting all invocations in one single message so they run in parallel:

      If the perplexity backend is selected and the MCP tool perplexity_search from the MCP server search-perplexity is available:

      If the brave backend is selected and the MCP tool brave_web_search from the MCP server search-brave is available:

      If the exa backend is selected and the MCP tool web_search_exa from the MCP server search-exa is available:

      If the websearch backend is selected and the tool WebSearch (or, if it is not available, the tool web_search) is available:

      If none of the selected backends could be invoked -- because no corresponding tool is available -- only output the following and then immediately STOP processing the entire current skill:

    3. Consolidate all responses into the Web facts : merge overlapping information, drop irrelevant and unsourced information, and keep every remaining fact together with its source URL. Do not output anything.

  3. Ground in the Project:

    1. Resolve the artifact kinds spec, code, docs, and infr to their project-relative file lists:

    2. From these file lists, determine the files (or their parts) which are relevant for and -- the specification parts, source code modules, interfaces, and symbols, the documentation, and the build, test, and deployment configuration the topic touches or depends on -- and read them, strictly read-only (never change, stage, or commit anything). Condense their relevant project facts -- the current state, existing decisions, conventions, constraints, and terminology -- each with its project-relative file path, into . Do not output anything.

  4. Synthesize the Research Report:

    Call the ase_timestamp(format: "yyyy-LL-dd HH:mm") tool of the ase MCP server and set to the text field of its response. Then set to the research section of this run with the following , bounded to about 300 lines and at most 10 findings (the most relevant ones), where every line of every part is broken after about 100 characters, and where a part without any content states (none):

    Researched:

    Findings

    1. : () [...]

    Project Grounding

    • <project-file/>: [...]

    Assessment

    Recommendations

    • : [...]

    Here the Findings are the most relevant Web facts of , each with its source URL, the Project Grounding are the most relevant project facts of , each with its project-relative file path, the Assessment states in 3-8 sentences how the findings apply to the project, including the gaps (what the project lacks) and the conflicts (where the project or deviates from the findings), and the Recommendations are the concrete, actionable consequences for . You MUST NOT invent any finding, source URL, or project fact which is not backed by resp. . The section MUST NOT contain a line consisting of just ---. Do not output anything.

  5. Attach the Research Report:

    1. Persist: update as follows and save it, where a refused save restarts this sub-step:

      1. If the backmatter of contains an attachment block with the Type key value text/markdown; charset=utf-8; kind="research", it carries the sections of earlier research runs: fetch its payload via the ase_task_attachment(id: "<ase-task-id/>", type: "text/markdown; charset=utf-8; kind=\"research\"") tool of the ase MCP server, whose text output field is the payload verbatim, and set to it, followed by an empty line and , so the sections accumulate in chronological order. Otherwise, set to and append a new attachment block to the backmatter of .

      2. Set the keys of this attachment block according to the plan : Type to text/markdown; charset=utf-8; kind="research", Desc to (truncated to at most 60 characters, ending in … if truncated), Created to its already present value (or to for a new block), Modified to , and Data to as a |4+ literal block scalar, with every line -- including empty lines -- indented by exactly 4 spaces.

      3. Change nothing else of : especially, do not change the Status: key, pass the Effort: key through verbatim (the task store drops it on its own if the body changed), and pass all other attachment blocks through verbatim (with their elided Data markers).

      4. Call the ase_task_save(id: "<ase-task-id/>", text: "<plan/>", base: "<tag/>") tool of the ase MCP server, so a change of the plan made meanwhile by anybody else is merged, and the save is refused only if that change touched the same parts. This ase_task_save MCP tool call is the only permitted way to persist the plan -- NEVER write the plan file via Write/Edit or by executing a shell command.

        • On success, set research attached, or research attached, plan refined if the body was changed by sub-step 3 above.

        • If the save is refused because the plan was changed meanwhile, reload and as in step 1.4 and restart this sub-step 2 (keeping ), at most three times in total, and afterwards set failed: plan changed concurrently.

        • On any other error , set failed: .

    2. Report:

    3. Finally, give the closing hint by expanding the following (which, depending on the configured , may expand into nothing and hence emit no output at all), and then STOP processing the entire current skill:

add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 114kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 114kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 114kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 114kUpdated Claude CodeCodexVerifiedInstall