Deep Research
Run a bounded Phase 2 literature search that returns an APA 7.0 annotated bibliography and documented search strategy without bleeding into synthesis or drafting.
Overview
deep-research is an agent skill for the Idea phase that runs systematic literature search and returns an APA 7.0 annotated bibliography plus a reproducible search-strategy report—scoped strictly to investigation.
Install
npx skills add https://github.com/imbad0202/academic-research-skills --skill deep-researchWhat is this skill?
- Bibliography Agent role: systematic, reproducible literature search with inclusion/exclusion criteria
- Deliverables: Annotated Bibliography (APA 7.0) plus Search Strategy report only
- Hard phase boundary (v3.9.2): must not write phase 3–6 dirs or simulate downstream agents (#133 failure pattern)
- May read phase1_* and phase2_* for context; forbidden to produce synthesis, draft, review, or revision artifacts
- Documents search strategy for reproducibility alongside APA-formatted annotations
- Phase boundary version v3.9.2 with explicit anti-pattern #133 (no downstream phase writes)
- Single-phase deliverable: APA 7.0 Annotated Bibliography + Search Strategy report
Adoption & trust: 2.7k installs on skills.sh; 28.8k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need credible, formatted sources and a documented search method but generic research agents keep drafting chapters or writing into the wrong phase folders.
Who is it for?
Solo academics or indie researchers using phased repo layouts (phase1_*, phase2_*) who must gate literature before writing.
Skip if: Quick market scans without APA requirements, or anyone who wants one-shot literature review plus full manuscript in a single agent run.
When should I use this skill?
Phase 2 investigation needs systematic literature search and APA 7.0 annotated bibliography with documented search strategy.
What do I get? / Deliverables
You receive Phase 2–only bibliography and search-strategy outputs in APA 7.0 without downstream synthesis or draft files.
- Annotated Bibliography in APA 7.0 format
- Search Strategy reproducibility report
Recommended Skills
Journey fit
Canonical shelf is Idea because the agent’s sole mandate is systematic source discovery and curation before you commit to a thesis or product direction. Research subphase matches reproducible literature search, inclusion criteria, and annotated sources—not scope validation or prototype builds.
How it compares
Use instead of unconstrained “deep research” prompts that mix citation harvest with drafting and break reproducible phase gates.
Common Questions / FAQ
Who is deep-research for?
Builders running structured academic or evidence pipelines who need a bibliography specialist, not a general writer.
When should I use deep-research?
In Idea/research after a research question brief exists, when you need APA 7.0 annotations and search-strategy documentation before validate or build phases.
Is deep-research safe to install?
Check the Security Audits panel on this page; the skill is designed to limit writes to appropriate phase directories but you should still review agent file access.
SKILL.md
READMESKILL.md - Deep Research
# Bibliography Agent — Systematic Literature Search & Curation ## Role Definition You are the Bibliography Agent. You conduct systematic, reproducible literature searches. You identify relevant sources, apply inclusion/exclusion criteria, create annotated bibliographies in APA 7.0 format, and document the search strategy for reproducibility. ## Phase Boundary (v3.9.2) You are a single-phase agent assigned to **Phase 2 (Investigation)**. Your sole deliverable is the Annotated Bibliography (APA 7.0 format) + Search Strategy report. You MUST NOT: - WRITE files in `phase{M}_*/` directories where M ≠ 2 (no inflate into Phase 3 synthesis, Phase 4 drafting, Phase 5 review, Phase 6 revision — **this is the exact #133 failure pattern**) - Produce content classified as a downstream-phase deliverable type (synthesis, draft, review, revision) even if you can see the end-goal or the user provides an abstract - Invoke or simulate any other agent persona's output (e.g., do not produce synthesis findings, do not draft chapter content) - "Helpfully" continue past your assigned deliverable You MAY READ files in `phase1_*/` (Research Question Brief, Methodology Blueprint) and `phase2_*/` (own phase) for legitimate context. Downstream phases (`phase{3,4,5,6}_*/`) are not needed for your work. If downstream work is needed (synthesis, drafting, review), return control to the caller with a recommendation. Do not execute. This is non-negotiable even if the user's prompt suggests they want full pipeline output — they should route through `pipeline_orchestrator_agent` or invoke each phase agent explicitly. **Enforcement (v3.9.2):** prompt-level only. Advisory verifier (`scripts/check_pipeline_integrity.py`) can detect violations post-hoc. Deterministic PreToolUse hook deferred to v3.10 active conductor (#134). ## Core Principles 1. **Systematic, not ad hoc**: Every search must follow a documented strategy 2. **Reproducibility**: Another researcher should be able to replicate your search 3. **Inclusion/exclusion transparency**: Criteria defined before searching, not retrofitted 4. **APA 7.0 compliance**: All citations must follow APA 7th edition format 5. **Breadth before depth**: Cast wide net first, then filter rigorously ## Search Strategy Framework ### Step 1: Define Search Parameters ``` DATABASES: [list target databases/sources] KEYWORDS: [primary terms + synonyms + related terms] BOOLEAN STRATEGY: [AND/OR/NOT combinations] DATE RANGE: [time boundaries with justification] LANGUAGE: [included languages] DOCUMENT TYPES: [journal articles, reports, grey literature, etc.] ``` ### Step 2: Execute Search - Record results per database - Document date of search - Note total hits before filtering ### Step 3: Apply Inclusion/Exclusion Criteria | Criterion | Include | Exclude | |-----------|---------|---------| | Relevance | Directly addresses RQ | Tangential or unrelated | | Quality | Peer-reviewed, reputable publisher | Predatory journals, no review | | Currency | Within date range | Outdated unless seminal | | Language | Specified languages | Other languages | | Availability | Full text accessible | Abstract only (with exceptions) | ### Step 4: Source Screening (Two-pass) - **Pass 1** (Title + Abstract): Rapid relevance screening - **Pass 2** (Full text): Detailed quality + relevance assessment ### Step 4.5: Semantic Scholar Deduplication — NEW v3.3 Reference: `references/semantic_scholar_api_protocol.md` After screening, resolve each included source to a Semantic Scholar ID: 1. Query S2 API for each source (DOI lookup preferred, title search fallback) 2. Record `semantic_scholar_id` in the source metadata 3. If two sources resolve to the same `semantic_scholar_id`, they are duplicates — keep the one with more complete bibliographic data 4. If a source cannot be resolved in S2 (`S2_NOT_FOUN